© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 2377
    Prev
    Next
    INDEX
    Explanations

    Website or computer code snippets

    oai_token-act-pair · gpt-3.5-turbo

    numerical patterns or identifiers

    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
    CLAIM
    -0.71
    Spread
    -0.69
    LOAD
    -0.69
    TPS
    -0.67
    POL
    -0.67
    Rating
    -0.67
    VEL
    -0.66
    Sync
    -0.65
    ILA
    -0.65
    Orderable
    -0.64
    POSITIVE LOGITS
    afa
    1.16
    ffe
    1.11
    aea
    1.11
    efe
    1.08
    ae
    1.08
    cf
    1.02
    aba
    1.00
    578
    0.97
    ba
    0.97
    cd
    0.97
    Activations Density 0.048%

    No Known Activations