© 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. 1-RES-JB
    11. 5466
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hoop
    -0.65
    govtrack
    -0.64
     Barron
    -0.63
    aren
    -0.63
    ikan
    -0.62
     Slash
    -0.62
     Brewer
    -0.62
     Haw
    -0.61
    ira
    -0.60
     Shade
    -0.60
    POSITIVE LOGITS
    pez
    0.82
    _>
    0.78
    >]
    0.75
    Reviewer
    0.73
    _-_
    0.73
    =]
    0.73
    ildo
    0.72
    IFIED
    0.70
    dfx
    0.69
    ifi
    0.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.