© 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. 10-RES-JB
    11. 21544
    Prev
    Next
    INDEX
    Explanations

    dates expressed as years

    oai_token-act-pair · gpt-3.5-turbo

    the letter "L" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dwindling
    -0.75
     peripheral
    -0.73
     recycling
    -0.70
     scattering
    -0.70
     Seah
    -0.69
     succession
    -0.69
     thwart
    -0.68
     strat
    -0.67
     fodder
    -0.67
     flowering
    -0.66
    POSITIVE LOGITS
    ï¸ı
    1.21
    agree
    1.04
    ï¸
    0.95
    love
    0.94
    ¢
    0.94
    Ïī
    0.93
    mand
    0.93
    mir
    0.92
    felt
    0.92
    know
    0.91
    Activations Density 0.116%

    No Known Activations