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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 24107
    Prev
    Next
    INDEX
    Explanations

    references to release dates and locations for various media

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the release of media or entertainment content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibur
    -0.97
    tre
    -0.79
    oute
    -0.78
    staking
    -0.74
    rous
    -0.71
    oeuv
    -0.68
    oulos
    -0.68
    bol
    -0.67
     disagree
    -0.67
    auld
    -0.66
    POSITIVE LOGITS
     theaters
    1.38
     conjunction
    1.28
     paperback
    1.10
     chronological
    1.00
     stores
    1.00
     tandem
    0.99
     cinem
    0.96
     Japan
    0.95
     commem
    0.95
     theat
    0.94
    Activations Density 0.146%

    No Known Activations