© 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. 2-RES-JB
    11. 8204
    Prev
    Next
    INDEX
    Explanations

    words related to laws and regulations, specifically about taxation on substances like alcohol and tobacco

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abi
    -0.86
     Algeria
    -0.83
    league
    -0.75
    bang
    -0.71
     {:
    -0.71
    saf
    -0.71
    ب
    -0.71
     Iraq
    -0.69
    inventoryQuantity
    -0.68
    QL
    -0.68
    POSITIVE LOGITS
    ribing
    0.74
    uctor
    0.74
    riber
    0.73
    icka
    0.70
    ucky
    0.68
    uct
    0.68
     SUN
    0.68
    ribed
    0.68
    ioch
    0.66
    ortium
    0.66
    Activations Density 0.000%

    No Known Activations