© 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. 2-RES-JB
    11. 18369
    Prev
    Next
    INDEX
    Explanations

    names or mentions related to the person Kaufman

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kaufman" and other specific identifiers, likely related to a person or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boards
    -0.76
    board
    -0.75
    lio
    -0.67
    carry
    -0.64
    ILE
    -0.63
    boys
    -0.63
     Login
    -0.62
    lia
    -0.61
     accomp
    -0.60
    Champ
    -0.60
    POSITIVE LOGITS
     Kaufman
    0.81
    uddin
    0.79
    audi
    0.76
     Horowitz
    0.75
    edi
    0.72
    uminati
    0.72
     Damon
    0.72
    etry
    0.72
    rov
    0.69
    ovsky
    0.69
    Activations Density 0.025%

    No Known Activations