© 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. 0-RES-JB
    11. 1142
    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
    abi
    -0.77
    ENTION
    -0.77
    worms
    -0.77
    worm
    -0.74
    ãĤ°
    -0.73
    rag
    -0.69
    ogram
    -0.68
    aban
    -0.66
    aus
    -0.62
    atown
    -0.62
    POSITIVE LOGITS
     flames
    0.63
    cyclopedia
    0.61
    [[
    0.61
     defends
    0.60
     grips
    0.58
    aily
    0.58
    felt
    0.58
    istrates
    0.57
     Moe
    0.57
    stable
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.