© 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. 3-RES-JB
    11. 1709
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aub
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
     Mercer
    -0.64
     Fruit
    -0.63
    ain
    -0.63
     Nut
    -0.62
     Neighbor
    -0.62
    Incre
    -0.62
     Nat
    -0.62
     Prediction
    -0.61
    POSITIVE LOGITS
    yip
    0.91
    xual
    0.79
    lease
    0.77
    essee
    0.71
    ederal
    0.68
    drops
    0.67
    aghan
    0.66
    ellar
    0.65
    cking
    0.64
    ctors
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.