© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32556
    Prev
    Next
    INDEX
    Explanations

    faces, expressions, and emotions, particularly focusing on smiles

    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
    +0.14
    0.7%
    326
    +0.12
    0.6%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.14
    0.20
    138
    +0.12
    0.17
    64
    +0.11
    -0.20
    Negative Logits
    NK
    -0.68
     deliberations
    -0.68
     Azerbai
    -0.66
     pige
    -0.63
     colle
    -0.61
     pigeon
    -0.60
     contrace
    -0.59
     Mandatory
    -0.59
     bloc
    -0.58
    raped
    -0.56
    POSITIVE LOGITS
    ingly
    0.80
    idity
    0.78
    iness
    0.75
    iem
    0.75
    eful
    0.74
    athon
    0.73
    ings
    0.73
    ous
    0.71
    sticks
    0.71
    fest
    0.70
    Activations Density 8.833%

    No Known Activations