© 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 EvalsExportsAPI 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. 12219
    Prev
    Next
    INDEX
    Explanations

    mentions of nuclear-related terms and concepts

    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
    +0.34
    1.1%
    565
    +0.17
    0.6%
    569
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.34
    0.07
    137
    +0.17
    0.04
    725
    +0.17
    0.04
    Negative Logits
    xus
    -1.09
    laus
    -1.09
    raised
    -1.08
    AGES
    -1.05
    ean
    -1.04
     Ort
    -1.03
    anza
    -1.00
    tyard
    -1.00
    ript
    -1.00
    lay
    -0.99
    POSITIVE LOGITS
     deterrent
    1.36
     deterrence
    1.30
     warheads
    1.24
     weapons
    1.24
     reactors
    1.23
     bombs
    1.22
     reactor
    1.22
     submarine
    1.20
     submarines
    1.19
     bomb
    1.17
    Activations Density 0.844%

    No Known Activations