© 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. 2816
    Prev
    Next
    INDEX
    Explanations

    information related to security measures, law enforcement activities, surveillance tactics, and legal agreements

    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
    743
    +0.13
    0.5%
    360
    +0.11
    0.5%
    111
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.13
    0.20
    739
    +0.11
    0.04
    310
    +0.10
    0.08
    Negative Logits
     proble
    -0.80
     lately
    -0.78
     Beng
    -0.78
    èª
    -0.77
     behavi
    -0.75
    ¥µ
    -0.72
     turbulence
    -0.72
     misunderstood
    -0.71
    natureconservancy
    -0.70
    ukemia
    -0.70
    POSITIVE LOGITS
     preferably
    1.12
     optionally
    1.07
     hereafter
    1.05
     Registration
    0.92
     hereby
    0.87
    shall
    0.86
     Mondays
    0.85
     annually
    0.83
    ichever
    0.83
     designate
    0.82
    Activations Density 5.948%

    No Known Activations