© 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. 1-RES-JB
    11. 8041
    Prev
    Next
    INDEX
    Explanations

    mentions of governors and political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to state governors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossier
    -0.72
    Else
    -0.71
    ded
    -0.66
    200000
    -0.66
    CV
    -0.66
    former
    -0.66
    itton
    -0.65
     Osw
    -0.64
    zo
    -0.64
    00200000
    -0.64
    POSITIVE LOGITS
     governors
    1.11
    hips
    1.04
     Governors
    0.92
    agascar
    0.90
    iosity
    0.82
     overse
    0.79
     Cosponsors
    0.79
     councils
    0.79
    rats
    0.79
    ettings
    0.78
    Activations Density 0.007%

    No Known Activations