© 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. 4960
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to medicine and research, including anatomical terms and experimental procedures

    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
    447
    +0.18
    0.7%
    89
    +0.12
    0.5%
    369
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.18
    0.01
    404
    +0.12
    0.09
    464
    +0.12
    0.09
    Negative Logits
    hirt
    -0.80
    bern
    -0.79
    ktop
    -0.75
    enhagen
    -0.73
    ascus
    -0.72
    redo
    -0.69
    glers
    -0.68
     explan
    -0.66
     drawer
    -0.65
     Borders
    -0.64
    POSITIVE LOGITS
    aic
    0.82
    opa
    0.79
    ctory
    0.79
     Blossom
    0.78
    γ
    0.77
    govtrack
    0.76
    à¥
    0.75
    utical
    0.75
    nown
    0.75
    BILITIES
    0.72
    Activations Density 13.069%

    No Known Activations