© 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. 8520
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures, particularly Mitt Romney

    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
    288
    +0.28
    0.9%
    621
    +0.18
    0.6%
    527
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.28
    0.05
    346
    +0.18
    0.05
    288
    +0.17
    0.06
    Negative Logits
    ĨĴ
    -1.27
    ivated
    -1.23
    ĵĺ
    -1.21
    ¥ŀ
    -1.18
     Flavoring
    -1.17
    sembly
    -1.16
     proble
    -1.16
    terday
    -1.13
    uador
    -1.11
     antioxid
    -1.10
    POSITIVE LOGITS
     Romney
    1.52
    Romney
    1.28
    thal
    1.25
    stein
    1.07
    enstein
    1.06
     Mamm
    1.03
    tto
    1.02
    tor
    1.02
    fish
    1.01
    rade
    1.00
    Activations Density 0.564%

    No Known Activations