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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3437
    Prev
    Next
    INDEX
    Explanations

    keywords related to the September 11 terrorist attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to the dates surrounding the September 11 attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PLIC
    -0.73
    mbuds
    -0.68
    cour
    -0.65
    LLOW
    -0.63
    itled
    -0.63
     blush
    -0.62
    reprene
    -0.62
    SHIP
    -0.61
     carrot
    -0.61
    veland
    -0.61
    POSITIVE LOGITS
     11
    1.01
     Attacks
    0.98
     attacks
    0.92
     2001
    0.88
    ghazi
    0.84
    ocaust
    0.83
     Massacre
    0.82
    attacks
    0.81
     bombings
    0.80
     massacres
    0.80
    Activations Density 0.052%

    No Known Activations