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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 10498
    Prev
    Next
    INDEX
    Explanations

    numerical patterns, specifically those starting with the word "voluntary"

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific term or keyword, likely related to "Vol 3"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rampage
    -0.68
    LESS
    -0.68
     Synd
    -0.67
     Rebels
    -0.65
     synd
    -0.64
    riad
    -0.62
     franc
    -0.62
     Sunder
    -0.62
     MacArthur
    -0.62
     Pearce
    -0.61
    POSITIVE LOGITS
    atile
    1.52
    untary
    1.50
    atility
    1.46
    umes
    1.31
    untarily
    1.18
    unte
    1.09
    leys
    1.07
    cano
    1.00
    umn
    0.90
    UME
    0.88
    Activations Density 0.031%

    No Known Activations