© 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. 6971
    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
    ãģ®éŃĶ
    -0.75
    enges
    -0.75
    Duration
    -0.73
    itaire
    -0.72
    Contents
    -0.70
    capacity
    -0.68
    reath
    -0.65
    Reviewer
    -0.65
    prototype
    -0.64
     "$:/
    -0.64
    POSITIVE LOGITS
    omers
    0.74
     Beir
    0.74
    ewater
    0.69
     Howell
    0.64
    ainer
    0.64
     blames
    0.63
    velt
    0.62
     Hog
    0.62
     unsur
    0.61
     Gork
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.