© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 32417
    Prev
    Next
    INDEX
    Explanations

    verbs related to knowledge acquisition or intellectual comprehension

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns preceding the word "understanding"

    oai_token-act-pair · gpt-3.5-turboTriggered by @jordan
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.29
    1.2%
    679
    +0.14
    0.6%
    549
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.29
    0.18
    385
    +0.14
    0.20
    393
    +0.14
    0.28
    Negative Logits
    onies
    -0.89
    hire
    -0.71
    quer
    -0.70
     exhib
    -0.67
    strip
    -0.67
    yss
    -0.66
    cake
    -0.65
    onte
    -0.65
    picking
    -0.65
    cow
    -0.64
    POSITIVE LOGITS
     Understanding
    0.98
     comprehension
    0.90
     understanding
    0.87
     Understand
    0.86
    ably
    0.84
    ledge
    0.79
    ability
    0.78
     WHY
    0.76
    ¿½
    0.76
    éĸ
    0.74
    Activations Density 11.264%

    No Known Activations