© 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 EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12357
    Prev
    Next
    INDEX
    Explanations

    phrases related to understanding or lack of understanding in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    679
    +0.18
    0.6%
    739
    +0.16
    0.5%
    455
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.18
    0.06
    56
    +0.16
    0.04
    1
    +0.16
    0.04
    Negative Logits
    onies
    -1.09
    onto
    -0.99
    boro
    -0.96
     notor
    -0.95
    pload
    -0.95
     stunt
    -0.91
    pi
    -0.90
    haw
    -0.90
    onte
    -0.89
    quer
    -0.87
    POSITIVE LOGITS
    ably
    1.22
     Understanding
    1.16
     WHY
    1.15
    ances
    1.15
     Understand
    1.14
    ¿½
    1.04
     how
    1.01
     why
    1.00
     understanding
    1.00
     comprehension
    0.99
    Activations Density 0.673%

    No Known Activations