© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 20356
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Keith"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name 'Keith'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĺħ
    -0.81
    xual
    -0.79
    cele
    -0.76
    ahime
    -0.72
    perse
    -0.71
    worldly
    -0.70
     inflamm
    -0.69
    icted
    -0.67
    nces
    -0.66
    )=(
    -0.66
    POSITIVE LOGITS
     Keith
    0.99
    otle
    0.89
    rett
    0.89
     Alexander
    0.87
     Ellison
    0.84
    rette
    0.76
     Jarrett
    0.75
     Davidson
    0.74
    mare
    0.73
    rey
    0.72
    Activations Density 0.002%

    No Known Activations