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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 3105
    Prev
    Next
    INDEX
    Explanations

    objects that can potentially cause harm

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Helpful
    -0.77
     Marketable
    -0.73
    ecause
    -0.72
     Flavoring
    -0.70
     Tradable
    -0.70
     Universities
    -0.69
    Ĭ±
    -0.68
    Ranked
    -0.68
     Limited
    -0.67
    cale
    -0.66
    POSITIVE LOGITS
    iest
    0.96
    osphere
    0.94
     itself
    0.93
    ultimate
    0.89
    maker
    0.78
    liest
    0.77
     portion
    0.77
     disappears
    0.76
    hest
    0.72
     maker
    0.71
    Activations Density 0.583%

    No Known Activations