© 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
    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. 14304
    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
     gob
    -0.73
     bol
    -0.72
    apo
    -0.71
    undo
    -0.71
    weet
    -0.71
     simul
    -0.70
     SB
    -0.69
    irtual
    -0.69
    tu
    -0.65
    pa
    -0.64
    POSITIVE LOGITS
    Dialogue
    1.10
    pmwiki
    0.86
    Dead
    0.78
     unlaw
    0.73
    Stretch
    0.72
    Rh
    0.72
    ALSE
    0.72
    Sham
    0.71
    OTOS
    0.70
    UFF
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.