© 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. 3325
    Prev
    Next
    INDEX
    Explanations

    terms related to historical events, specifically the Civil War

    oai_token-act-pair · gpt-3.5-turbo

    references to the Civil War and Civil Rights

    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
    asus
    -0.77
    cca
    -0.76
    TOP
    -0.76
    RAM
    -0.73
    gger
    -0.70
    LOC
    -0.68
    agame
    -0.68
    url
    -0.68
    WARD
    -0.65
    target
    -0.65
    POSITIVE LOGITS
    izational
    1.17
    Civil
    0.93
     Civil
    0.91
    izations
    0.86
    ivil
    0.84
     Liberties
    0.82
    isations
    0.82
     Rights
    0.81
     Aviation
    0.77
    auld
    0.75
    Activations Density 0.005%

    No Known Activations