© 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. 10971
    Prev
    Next
    INDEX
    Explanations

    discussions or descriptions related to economic activities and political interactions

    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
    393
    +0.15
    0.8%
    739
    +0.09
    0.5%
    449
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.15
    0.15
    484
    +0.09
    0.15
    393
    +0.09
    0.16
    Negative Logits
    conservancy
    -0.84
    cffffcc
    -0.78
    ikan
    -0.76
    othal
    -0.75
    iqueness
    -0.74
    actionDate
    -0.71
    PF
    -0.67
    ¶
    -0.67
    Footnote
    -0.66
    userc
    -0.64
    POSITIVE LOGITS
    romeda
    0.79
     subscribe
    0.70
     explore
    0.69
     Titus
    0.67
    rea
    0.63
     enjoy
    0.60
     congratulated
    0.60
     receive
    0.59
     secure
    0.59
     learn
    0.59
    Activations Density 2.008%

    No Known Activations