© 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. 11-RES-JB
    11. 7085
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events, specifically those related to the American Civil War and civil rights movements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gger
    -0.67
     scratch
    -0.67
    ugi
    -0.64
     dipping
    -0.63
     spoiler
    -0.62
     branded
    -0.61
     sque
    -0.61
    GY
    -0.61
     flat
    -0.61
    cki
    -0.61
    POSITIVE LOGITS
     Liberties
    1.46
     Rights
    1.22
    izations
    1.13
    ian
    1.05
    izational
    1.02
    isations
    0.96
    ized
    0.93
     War
    0.92
    ization
    0.92
     Service
    0.91
    Activations Density 0.015%

    No Known Activations