© 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. 6857
    Prev
    Next
    INDEX
    Explanations

    references to historical empires, particularly the "Empire"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Empire" and related terms

    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
    paces
    -0.78
    matter
    -0.76
    yrics
    -0.75
    eret
    -0.73
    ociate
    -0.73
    hift
    -0.73
    onto
    -0.72
    giving
    -0.71
    arten
    -0.70
    electric
    -0.70
    POSITIVE LOGITS
     Strikes
    1.00
    perors
    0.84
     conquered
    0.81
     Augustus
    0.81
     Claud
    0.81
     Britann
    0.80
     Builder
    0.80
     Nero
    0.77
     Napoleon
    0.75
     overth
    0.75
    Activations Density 0.071%

    No Known Activations