© 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
    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. 10432
    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
    IER
    -0.73
    ARA
    -0.70
    ably
    -0.66
    EX
    -0.66
    rs
    -0.66
     Yards
    -0.65
    OUS
    -0.65
    ances
    -0.63
    able
    -0.61
    atl
    -0.59
    POSITIVE LOGITS
     world
    0.89
     throats
    0.80
     ancest
    0.77
    ãĥ¼ãĥĨ
    0.76
    ãĤ¨ãĥ«
    0.73
    EStreamFrame
    0.71
    ophone
    0.71
    liners
    0.70
    ãĤ¬
    0.70
     globe
    0.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.