© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 11947
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislation and political actions

    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
    360
    +0.16
    0.5%
    662
    +0.13
    0.4%
    700
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.16
    0.04
    758
    +0.13
    0.03
    700
    +0.12
    0.03
    Negative Logits
     IPM
    -0.93
    ilts
    -0.92
     Skull
    -0.91
     Ridley
    -0.90
     Monk
    -0.86
    anmar
    -0.85
     Celest
    -0.82
     Nero
    -0.81
     Hats
    -0.81
     intimidated
    -0.81
    POSITIVE LOGITS
    selves
    1.11
    sight
    1.11
    dra
    1.04
    ships
    0.99
    lab
    0.99
    la
    0.98
    draw
    0.97
    late
    0.97
    nesota
    0.95
    city
    0.94
    Activations Density 0.316%

    No Known Activations