© 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. 4986
    Prev
    Next
    INDEX
    Explanations

    references to interactions and relationships between people

    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
    756
    +0.12
    0.5%
    667
    +0.12
    0.5%
    717
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.20
    762
    +0.12
    0.28
    354
    +0.11
    0.16
    Negative Logits
    terness
    -0.84
    payers
    -0.83
     Citation
    -0.79
    geries
    -0.79
    ocre
    -0.78
    gate
    -0.77
    violent
    -0.75
    htaking
    -0.73
    cussion
    -0.70
    een
    -0.70
    POSITIVE LOGITS
     own
    1.07
     hoped
    0.86
     intend
    0.82
     wished
    0.82
    deals
    0.79
     hope
    0.76
     preferred
    0.73
    \\
    0.73
    HF
    0.73
    Shares
    0.72
    Activations Density 16.871%

    No Known Activations