© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 19269
    Prev
    Next
    INDEX
    Explanations

    specific references to terrorist attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to notable events and attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouble
    -0.83
    igmatic
    -0.75
    rils
    -0.74
    inline
    -0.72
     specialize
    -0.71
    genre
    -0.71
    ventional
    -0.70
    ertain
    -0.70
    pees
    -0.70
    oing
    -0.70
    POSITIVE LOGITS
     JFK
    0.83
     Pearl
    0.79
     Bell
    0.76
     Zam
    0.75
     Notre
    0.73
     Yellowstone
    0.72
     Gal
    0.72
     Titus
    0.72
     Martha
    0.72
     Copenhagen
    0.72
    Activations Density 0.481%

    No Known Activations