© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 Local
    9. 6-RES_SCL-AJT
    11. 33778
    Prev
    Next
    INDEX
    Explanations

    athletes and sports events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    99
    +0.20
    0.9%
    269
    +0.12
    0.5%
    346
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.20
    0.16
    326
    +0.12
    0.27
    288
    +0.11
    0.26
    Negative Logits
    lying
    -0.76
    ave
    -0.74
    Interstitial
    -0.73
    leon
    -0.73
    les
    -0.73
    stood
    -0.71
    lean
    -0.71
     Lucia
    -0.69
    lesiastical
    -0.68
    CENT
    -0.68
    POSITIVE LOGITS
    berman
    0.89
     Hots
    0.87
    zac
    0.85
     Fey
    0.82
    rey
    0.81
    inished
    0.81
    reys
    0.80
    plings
    0.80
    wark
    0.79
    psey
    0.79
    Activations Density 11.675%

    No Known Activations