© 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. 6-RES-JB
    11. 9302
    Prev
    Next
    INDEX
    Explanations

    names of people with the name "James"

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those with the first name "James."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hesive
    -0.72
    opausal
    -0.68
     Haitian
    -0.64
     wart
    -0.63
     "%
    -0.63
    incial
    -0.63
    ishable
    -0.62
    earable
    -0.61
    ascript
    -0.61
    theless
    -0.60
    POSITIVE LOGITS
    wer
    0.69
    acca
    0.69
    ington
    0.66
    aman
    0.64
    chel
    0.62
    lling
    0.61
    stad
    0.60
    inka
    0.60
    enes
    0.60
    EStream
    0.59
    Activations Density 0.121%

    No Known Activations