© 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. 45696
    Prev
    Next
    INDEX
    Explanations

    descriptions related to financial matters and governmental policies

    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
    316
    +0.11
    0.5%
    437
    +0.10
    0.4%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    514
    +0.11
    0.05
    559
    +0.10
    0.05
    501
    +0.10
    0.07
    Negative Logits
     retard
    -0.86
    powers
    -0.70
    anger
    -0.61
     advoc
    -0.61
     nightly
    -0.61
     rou
    -0.60
     Afgh
    -0.59
    ²¾
    -0.58
     rall
    -0.58
     quiet
    -0.58
    POSITIVE LOGITS
    ertodd
    0.84
    Credit
    0.78
     Drawing
    0.75
     Credit
    0.75
     Depot
    0.74
    enhagen
    0.72
     Photo
    0.72
     Institution
    0.71
    patrick
    0.71
     Transfer
    0.70
    Activations Density 5.716%

    No Known Activations