© 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. 4-RES-JB
    11. 15245
    Prev
    Next
    INDEX
    Explanations

    references to wars or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to various "wars" across different contexts and themes

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

    No Comments

    Negative Logits
    AUT
    -0.76
    gow
    -0.75
    Asset
    -0.75
    YL
    -0.68
    alties
    -0.65
    Safety
    -0.64
    OGR
    -0.64
    Known
    -0.64
    ritch
    -0.64
    SOURCE
    -0.63
    POSITIVE LOGITS
    hips
    1.19
    hip
    1.13
    lords
    0.92
     wars
    0.90
    pite
    0.87
    poons
    0.86
    mith
    0.85
    kies
    0.84
     waged
    0.83
     raged
    0.82
    Activations Density 0.018%

    No Known Activations