© 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. 10-RES-JB
    11. 18978
    Prev
    Next
    INDEX
    Explanations

    references to the historical event or location of Pearl Harbor

    oai_token-act-pair · gpt-3.5-turbo

    references to Pearl Harbor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    es
    -0.80
    ed
    -0.72
    ulously
    -0.70
    elsius
    -0.69
    dayName
    -0.66
    arbon
    -0.65
     Angry
    -0.64
    hed
    -0.64
    CRIP
    -0.62
     rigs
    -0.61
    POSITIVE LOGITS
    ogue
    0.76
    aith
    0.75
     Harbour
    0.75
    atform
    0.73
    ãħĭ
    0.72
    Ĥ¬
    0.69
    ivot
    0.68
    istic
    0.68
    itz
    0.67
    omever
    0.66
    Activations Density 0.095%

    No Known Activations