Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 126
    Prev
    Next
    INDEX
    Explanations

    titles or references to specific volumes or publications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Vol" and its variations, likely indicating a focus on volume numbers in publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riad
    -0.78
     Synd
    -0.68
     Pearce
    -0.68
     Rampage
    -0.66
     Turing
    -0.66
    merce
    -0.63
     Gauntlet
    -0.63
     Defenders
    -0.60
     Clarkson
    -0.60
     Annotations
    -0.60
    POSITIVE LOGITS
    atile
    1.36
    atility
    1.34
    untary
    1.25
    umes
    1.20
    unte
    0.97
    leys
    0.95
    untarily
    0.90
    cano
    0.88
    vol
    0.84
    itionally
    0.83
    Activations Density 0.016%

    No Known Activations