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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2659
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to personal names like "Guy."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Guy."

    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
    rawdownloadcloneembedreportprint
    -0.72
    undai
    -0.68
    arily
    -0.64
    EMBER
    -0.63
    icts
    -0.62
    rums
    -0.60
     CTR
    -0.59
    arching
    -0.58
    ski
    -0.58
     womb
    -0.58
    POSITIVE LOGITS
     Faw
    1.24
    brush
    1.06
     Cecil
    0.88
    enne
    0.88
     Laf
    0.86
    fred
    0.83
    mond
    0.80
    agne
    0.80
     Sabha
    0.77
    aign
    0.76
    Activations Density 0.024%

    No Known Activations