© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1659
    Prev
    Next
    INDEX
    Explanations

    timestamps and user activities on online forums

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    27
    +0.14
    0.6%
    141
    +0.11
    0.5%
    90
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.14
    0.01
    365
    +0.11
    0.01
    271
    +0.11
    0.01
    Negative Logits
    opathy
    -0.73
     fit
    -0.73
    fit
    -0.72
    ãĥ³ãĤ¸
    -0.72
    nah
    -0.71
    gger
    -0.69
    ERG
    -0.68
     Zucker
    -0.68
     substitute
    -0.66
    othe
    -0.65
    POSITIVE LOGITS
    ategory
    0.81
    Activity
    0.78
    aceous
    0.74
    itures
    0.72
    irements
    0.72
    ertodd
    0.71
    inguished
    0.70
     queues
    0.69
    htaking
    0.67
    ascade
    0.67
    Activations Density 0.045%

    No Known Activations