© 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. 8-RES-JB
    11. 20217
    Prev
    Next
    INDEX
    Explanations

    references to Osama bin Laden

    oai_token-act-pair · gpt-3.5-turbo

    references and mentions of Osama bin Laden

    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
    anwhile
    -0.78
    ktop
    -0.73
    hips
    -0.69
    theless
    -0.68
    mble
    -0.66
    laus
    -0.66
     Jagu
    -0.66
    terday
    -0.65
    ITH
    -0.65
     Parish
    -0.65
    POSITIVE LOGITS
    omial
    1.73
    ocular
    1.71
     Laden
    1.55
    nington
    1.15
    ning
    1.04
    jamin
    1.00
    ned
    1.00
    thood
    0.97
    utils
    0.93
    ational
    0.92
    Activations Density 0.042%

    No Known Activations