© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11629
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people, specifically names starting with "Malcolm."

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly focusing on the name "Malcolm."

    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
    rums
    -0.80
    sburgh
    -0.72
    urat
    -0.69
    ricular
    -0.67
    een
    -0.66
    eva
    -0.65
    ski
    -0.64
    tails
    -0.64
     extremes
    -0.63
    mble
    -0.62
    POSITIVE LOGITS
     Turnbull
    1.16
    colm
    0.98
    sey
    0.91
     Glad
    0.90
     Fraser
    0.85
     Reynolds
    0.84
     Malcolm
    0.80
     Tucker
    0.79
     Blanc
    0.76
     Mug
    0.76
    Activations Density 0.017%

    No Known Activations