© 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. 6479
    Prev
    Next
    INDEX
    Explanations

    historical events or terms related to significant organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to historical political entities and events, particularly related to the Soviet Union

    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
    bugs
    -0.69
     sneaky
    -0.63
     slippery
    -0.62
     vulnerability
    -0.62
     smells
    -0.61
     horm
    -0.61
    antis
    -0.60
     mosquit
    -0.60
     whistleblowers
    -0.60
    cipled
    -0.60
    POSITIVE LOGITS
     renamed
    0.91
     respectively
    0.73
     merged
    0.73
     successor
    0.73
     disbanded
    0.72
     consecut
    0.70
     officially
    0.70
     debuted
    0.68
    .).
    0.68
     Interstate
    0.67
    Activations Density 1.172%

    No Known Activations