© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 21111
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abase
    -0.76
    rings
    -0.69
    rocket
    -0.69
    lux
    -0.67
    eret
    -0.66
    properties
    -0.66
     CITY
    -0.66
     Leban
    -0.64
    etter
    -0.64
     dimensions
    -0.63
    POSITIVE LOGITS
    Reviewer
    0.89
    bill
    0.65
    raf
    0.65
     trending
    0.63
    mary
    0.63
     Flavoring
    0.63
     distraction
    0.62
    ADVERTISEMENT
    0.62
     Favor
    0.61
     awa
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.