© 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. 1-RES-JB
    11. 11338
    Prev
    Next
    INDEX
    Explanations

    person names and company names containing the term "ucker"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Tucker" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orem
    -0.79
    raints
    -0.73
    arel
    -0.69
     circ
    -0.68
    metic
    -0.68
    orate
    -0.64
    adr
    -0.63
    orers
    -0.63
    sim
    -0.63
    s
    -0.62
    POSITIVE LOGITS
    ucker
    1.26
     Tucker
    0.86
    essee
    0.81
    buster
    0.78
    borg
    0.78
     Slug
    0.77
    geist
    0.77
     Carlson
    0.76
    onom
    0.75
    hole
    0.75
    Activations Density 0.010%

    No Known Activations