© 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. 2846
    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
    xual
    -1.05
    raid
    -0.88
    avorite
    -0.78
    redd
    -0.75
    endish
    -0.75
    oeuv
    -0.75
    ollah
    -0.74
    ptive
    -0.71
    door
    -0.71
    ey
    -0.70
    POSITIVE LOGITS
    bie
    0.67
    itiz
    0.66
     horizont
    0.62
     Grants
    0.61
     Caucasus
    0.60
     Garrett
    0.57
     Gru
    0.57
     Sheridan
    0.57
     Gou
    0.57
     joins
    0.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.