© 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. 20172
    Prev
    Next
    INDEX
    Explanations

    names associated with the first name "James"

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals, particularly those with the first name "James."

    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
    âĶĢâĶĢ
    -0.78
    âĸ¬
    -0.77
    âķIJ
    -0.72
     BIT
    -0.65
    cipline
    -0.63
    ãĥĦ
    -0.60
    é¾įå¥ij士
    -0.60
    âĸ¬âĸ¬
    -0.60
    ãĤ¨ãĥ«
    -0.60
    γ
    -0.60
    POSITIVE LOGITS
    sworth
    0.75
    apes
    0.68
    avan
    0.68
    wer
    0.68
    aman
    0.66
    erson
    0.66
    aird
    0.66
    lling
    0.65
    rage
    0.64
    ogg
    0.63
    Activations Density 0.106%

    No Known Activations