© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23113
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HUN
    -0.73
     Shepherd
    -0.71
     Sons
    -0.67
     Divinity
    -0.65
     Trin
    -0.65
     Hunter
    -0.64
     Done
    -0.64
     Written
    -0.64
    Marginal
    -0.63
    iar
    -0.62
    POSITIVE LOGITS
     leading
    1.79
     Leading
    0.94
    wcs
    0.83
    leading
    0.74
    udeb
    0.73
    awatts
    0.72
    ython
    0.70
     trailing
    0.69
    ourced
    0.69
    opens
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.