© 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. 8-RES-JB
    11. 20293
    Prev
    Next
    INDEX
    Explanations

    proper nouns or entities related to politics, government, and institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to government, judicial, and political entities or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uggle
    -0.75
    ugg
    -0.73
    atown
    -0.72
    hovah
    -0.71
    obyl
    -0.70
    resy
    -0.67
    akespeare
    -0.67
    zzle
    -0.66
    holes
    -0.66
    abiding
    -0.66
    POSITIVE LOGITS
     secretary
    1.23
     prosecutor
    1.09
    ptroller
    1.06
     council
    0.99
     deputy
    0.96
     administrator
    0.94
     parliamentary
    0.93
     envoy
    0.92
    mbudsman
    0.91
     chief
    0.91
    Activations Density 0.309%

    No Known Activations