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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23490
    Prev
    Next
    INDEX
    Explanations

    hashtags or specific words/phrases within text

    oai_token-act-pair · gpt-3.5-turbo

    references to identifying information or labels

    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
    ouple
    -0.75
    orthy
    -0.70
    uble
    -0.69
    enda
    -0.68
    enture
    -0.67
    ossier
    -0.65
    emetery
    -0.64
    ividual
    -0.63
     conclud
    -0.62
    licks
    -0.60
    POSITIVE LOGITS
     "#
    0.88
     USS
    0.83
     ``
    0.83
     '[
    0.80
     "@
    0.78
     "$
    0.76
     RED
    0.75
     of
    0.73
     \"
    0.73
     ''
    0.72
    Activations Density 0.177%

    No Known Activations