© 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. 2811
    Prev
    Next
    INDEX
    Explanations

    references to the superhero character "Clark" from the context of comics and novels

    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
    +0.19
    0.8%
    649
    +0.13
    0.5%
    642
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.09
    659
    +0.13
    0.06
    224
    +0.11
    0.06
    Negative Logits
    choes
    -1.02
    ntil
    -0.99
    Ïģ
    -0.94
    atis
    -0.94
    76561
    -0.89
    awaru
    -0.88
    urity
    -0.86
    olitan
    -0.85
    mble
    -0.85
    PDATE
    -0.84
    POSITIVE LOGITS
    ston
    1.16
    stown
    1.10
    istic
    0.98
    obyl
    0.97
     Ashton
    0.95
    istically
    0.94
     Kent
    0.92
    istics
    0.91
     Luthor
    0.88
    sey
    0.88
    Activations Density 1.108%

    No Known Activations