© 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. 36216
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and data organization

    oai_token-act-pair · gpt-3.5-turbo
    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
    +0.30
    1.3%
    393
    +0.18
    0.8%
    640
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.30
    0.42
    447
    +0.18
    0.44
    64
    +0.14
    -0.18
    Negative Logits
    llor
    -0.86
    NOW
    -0.75
    LOG
    -0.74
     incumb
    -0.73
    CLASSIFIED
    -0.71
     selves
    -0.68
    awei
    -0.67
     inval
    -0.66
    Voice
    -0.64
    EVA
    -0.64
    POSITIVE LOGITS
    efficiency
    1.23
     lieu
    1.20
    clusions
    1.16
     conjunction
    1.15
    ordinate
    1.12
     accordance
    1.10
    patient
    1.09
    animate
    1.08
     front
    1.08
     relation
    1.05
    Activations Density 11.000%

    No Known Activations