© 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. 6-RES-JB
    11. 8005
    Prev
    Next
    INDEX
    Explanations

    the last name "Walker" with varying numeric suffixes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Walker."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.93
    undai
    -0.87
    ritic
    -0.84
     mathemat
    -0.80
    sembly
    -0.79
    eon
    -0.78
    romeda
    -0.77
    ION
    -0.75
    н
    -0.73
     Lumpur
    -0.73
    POSITIVE LOGITS
    stown
    0.85
    Walker
    0.80
    esque
    0.78
    inson
    0.76
     Walker
    0.75
    ball
    0.75
    mania
    0.70
    chairs
    0.69
    tip
    0.69
    man
    0.68
    Activations Density 0.016%

    No Known Activations