© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 33870
    Prev
    Next
    INDEX
    Explanations

    names or words related to a person named "Matt"

    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
    187
    +0.13
    0.6%
    540
    +0.12
    0.6%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.13
    0.27
    160
    +0.12
    0.18
    255
    +0.12
    0.10
    Negative Logits
    éĹĺ
    -0.82
    ngth
    -0.73
    ¥ŀ
    -0.69
    æĸ¹
    -0.68
    ãĤī
    -0.67
    velength
    -0.66
    FUL
    -0.66
     cabbage
    -0.65
    CRIP
    -0.63
    hower
    -0.63
    POSITIVE LOGITS
    hematically
    1.46
    hematic
    1.35
    urity
    1.27
    rices
    1.23
    hemat
    1.22
    ilda
    1.14
    ches
    1.10
    hews
    1.08
    hew
    1.06
    ting
    1.05
    Activations Density 9.550%

    No Known Activations