© 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. 9-RES-JB
    11. 4329
    Prev
    Next
    INDEX
    Explanations

    references to legal or official matters, often related to terms such as "Offender" or "Official."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ§
    -0.90
    ãĤ©
    -0.73
     Jiu
    -0.67
     bund
    -0.66
    ãĥŃ
    -0.66
    ãĤ£
    -0.65
    ãĥ¥
    -0.62
    ISM
    -0.62
    zeb
    -0.61
    ãĥ£
    -0.60
    POSITIVE LOGITS
    ense
    1.22
    ices
    1.22
    ensive
    1.08
    enders
    1.03
    erence
    1.03
    enses
    0.97
    ered
    0.95
    ences
    0.95
    enger
    0.94
    rey
    0.94
    Activations Density 0.059%

    No Known Activations