© 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. 9-RES-JB
    11. 10383
    Prev
    Next
    INDEX
    Explanations

    mentions of names, possibly with a specific focus on names starting or containing "Rita," "Anita," "Juanita," "Conan," and "Doyle."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yg
    -0.95
    erate
    -0.88
    s
    -0.87
    er
    -0.87
    cript
    -0.87
    sin
    -0.83
    edo
    -0.82
    iful
    -0.81
    ijah
    -0.81
    son
    -0.81
    POSITIVE LOGITS
     Literature
    0.71
    pling
    0.69
     Rin
    0.69
     Moreno
    0.69
    odan
    0.68
    plings
    0.63
     Cout
    0.62
     Pole
    0.61
     Plate
    0.60
     Scotia
    0.60
    Activations Density 0.172%

    No Known Activations