© 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. 15094
    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
    athe
    -0.82
    RAW
    -0.77
    igh
    -0.73
    ATH
    -0.69
    idates
    -0.68
    OTH
    -0.68
    CENT
    -0.67
    NES
    -0.67
    ajor
    -0.65
    Jer
    -0.65
    POSITIVE LOGITS
    wagen
    0.81
    bucks
    0.80
    poons
    0.78
    urers
    0.71
     msec
    0.70
     recall
    0.69
     baskets
    0.66
     gems
    0.66
     quartz
    0.66
    poon
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.