© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 36861
    Prev
    Next
    INDEX
    Explanations

    statements related to collective actions or beliefs

    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
    +0.15
    0.7%
    578
    +0.12
    0.5%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.16
    216
    +0.12
    0.08
    513
    +0.12
    0.07
    Negative Logits
    lyn
    -0.83
    geon
    -0.80
    cale
    -0.77
    geons
    -0.77
    ĺħ
    -0.76
    xual
    -0.76
    ournal
    -0.76
    ocrates
    -0.76
    zbollah
    -0.75
    forth
    -0.74
    POSITIVE LOGITS
     bargaining
    1.25
     collective
    0.83
     membership
    0.81
    think
    0.81
     effort
    0.80
    ivities
    0.80
     noun
    0.78
     ACTIONS
    0.78
     member
    0.76
     endeavour
    0.75
    Activations Density 5.179%

    No Known Activations