© 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. 9176
    Prev
    Next
    INDEX
    Explanations

    names of individuals, possibly focusing on surnames

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles

    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
    rish
    -0.77
    orget
    -0.70
    pmwiki
    -0.69
     bearings
    -0.66
    bilt
    -0.66
    ilde
    -0.65
    hattan
    -0.63
     Medal
    -0.62
    sburgh
    -0.61
    puff
    -0.61
    POSITIVE LOGITS
    manship
    0.81
    hao
    0.77
    ciples
    0.75
    conn
    0.73
    ahime
    0.71
    terior
    0.70
    Introduced
    0.70
    RECT
    0.69
    WINDOWS
    0.67
     mustard
    0.65
    Activations Density 0.082%

    No Known Activations