© 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. 10-RES-JB
    11. 22157
    Prev
    Next
    INDEX
    Explanations

    names of politicians or celebrities, including both first and last names

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and figures in politics and sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enders
    -0.72
    ãĥ´ãĤ¡
    -0.66
    endered
    -0.66
    ieves
    -0.64
    GET
    -0.63
    radius
    -0.63
    ighter
    -0.63
    }{
    -0.62
    ãĥ¼ãĤ¯
    -0.62
    ends
    -0.59
    POSITIVE LOGITS
     lurking
    1.10
     looming
    1.04
     onboard
    1.01
     joining
    0.97
     alive
    0.97
     sitting
    0.95
     behind
    0.95
     intact
    0.95
     hanging
    0.94
     occupying
    0.92
    Activations Density 0.379%

    No Known Activations