© 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. 11979
    Prev
    Next
    INDEX
    Explanations

    political and governmental terms and references

    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
    +0.16
    0.5%
    616
    +0.13
    0.4%
    216
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.16
    0.09
    216
    +0.13
    0.08
    616
    +0.13
    0.07
    Negative Logits
    ander
    -1.12
    avery
    -1.06
    aping
    -1.05
    arsh
    -0.99
    ipedia
    -0.97
    opes
    -0.97
    opia
    -0.96
    iky
    -0.93
    aves
    -0.93
    asionally
    -0.93
    POSITIVE LOGITS
    stay
    1.49
     culprit
    1.33
     concern
    1.09
     source
    1.09
     artery
    1.09
     reason
    1.08
    stone
    1.08
     proponent
    1.06
     arteries
    1.06
     constituent
    1.04
    Activations Density 0.974%

    No Known Activations