© 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. 3-RES-JB
    11. 6343
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events, particularly World War II

    oai_token-act-pair · gpt-3.5-turbo

    references to World War II

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tile
    -0.80
    BOOK
    -0.80
    notes
    -0.79
    TOP
    -0.73
    à
    -0.72
     strengths
    -0.71
    wcsstore
    -0.70
    heet
    -0.69
    Points
    -0.67
    getting
    -0.67
    POSITIVE LOGITS
    hower
    0.85
     Anniversary
    0.84
    ohan
    0.80
     Memorial
    0.79
     era
    0.78
    ionage
    0.76
    engeance
    0.76
     Graves
    0.74
     1942
    0.73
     Britann
    0.73
    Activations Density 0.036%

    No Known Activations