© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11556
    Prev
    Next
    INDEX
    Explanations

    numeric data related to quantities or proportions

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable metrics and statistics related to various groups or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    din
    -0.74
    dit
    -0.73
    ullivan
    -0.71
    ovie
    -0.67
    cot
    -0.67
    zan
    -0.65
    reet
    -0.64
    ĺħ
    -0.64
    pell
    -0.63
    romy
    -0.61
    POSITIVE LOGITS
     varies
    1.20
     exceeds
    0.97
     of
    0.95
     depends
    0.95
     rises
    0.94
     ratio
    0.92
     grows
    0.92
     ranges
    0.91
     increases
    0.90
     difference
    0.90
    Activations Density 0.190%

    No Known Activations