© 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. 15198
    Prev
    Next
    INDEX
    Explanations

    references to the terrorist group Boko Haram

    oai_token-act-pair · gpt-3.5-turbo

    references to the Boko Haram militant group

    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
     McDonnell
    -0.78
    ality
    -0.76
     Gemini
    -0.74
    theless
    -0.74
     Pavilion
    -0.73
     Dragonbound
    -0.72
     guiActiveUnfocused
    -0.72
     Explain
    -0.71
    perture
    -0.71
    xual
    -0.71
    POSITIVE LOGITS
    ¯
    0.95
    marg
    0.94
    appings
    0.85
    ¶
    0.80
    awar
    0.79
    accompan
    0.77
    asp
    0.76
     Haram
    0.74
    Ń·
    0.73
    ³
    0.72
    Activations Density 0.017%

    No Known Activations