© 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. 8-RES-JB
    11. 1857
    Prev
    Next
    INDEX
    Explanations

    references to the term "Duke" with varying degrees of specificity and relevance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Duke."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verty
    -0.74
    ional
    -0.70
    heny
    -0.69
    hedon
    -0.67
    aging
    -0.66
    icity
    -0.66
    algia
    -0.66
    iped
    -0.66
    served
    -0.65
    atically
    -0.63
    POSITIVE LOGITS
    hyde
    1.08
    halla
    0.83
     lac
    0.79
    onna
    0.75
    ball
    0.74
    haus
    0.73
    aimon
    0.72
     Chapel
    0.69
     Divinity
    0.67
    hole
    0.67
    Activations Density 0.042%

    No Known Activations