© 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. 35259
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to places and people, particularly with the name "Ing" appearing as a notable activation

    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
    651
    +0.12
    0.6%
    699
    +0.12
    0.6%
    635
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.22
    326
    +0.12
    0.21
    323
    +0.11
    0.10
    Negative Logits
    ngth
    -0.81
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.77
    isers
    -0.70
    ĸļ
    -0.68
    puter
    -0.66
    TPPStreamerBot
    -0.66
     Leilan
    -0.65
     butterfly
    -0.63
     dysph
    -0.62
     ESC
    -0.61
    POSITIVE LOGITS
    raham
    0.94
    rosso
    0.87
    ueless
    0.84
    rates
    0.84
    rate
    0.81
    sm
    0.79
     Ing
    0.78
    mar
    0.77
    rador
    0.76
    urated
    0.76
    Activations Density 7.523%

    No Known Activations