© 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. 4-RES-JB
    11. 5090
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Gavin"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Gavin" and related variations, indicating a focus on a specific individual

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

    No Comments

    Negative Logits
    pard
    -0.83
    utenant
    -0.83
    rieg
    -0.69
    geon
    -0.68
    hibition
    -0.66
    ©¶æ
    -0.66
    telling
    -0.66
    paragraph
    -0.64
     Rove
    -0.64
    draw
    -0.63
    POSITIVE LOGITS
     Davies
    1.04
    avin
    0.83
     Gavin
    0.79
    loo
    0.68
    ÃŃa
    0.68
     Skywalker
    0.66
    ildo
    0.66
    atal
    0.66
    angel
    0.66
    aic
    0.65
    Activations Density 0.015%

    No Known Activations