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

    Neuronpedia

    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. 10-RES-JB
    11. 11357
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and programming

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to digital or online content and transactions

    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
     sorts
    -0.67
     kinds
    -0.66
     important
    -0.60
     correspond
    -0.59
     reasons
    -0.58
     approximately
    -0.58
    -0.57
     exciting
    -0.56
    Especially
    -0.55
     convenient
    -0.55
    POSITIVE LOGITS
    foundland
    0.83
    senal
    0.77
    ulic
    0.76
    ullivan
    0.76
     Conclusion
    0.75
    odium
    0.75
    zyme
    0.73
    thora
    0.72
    externalActionCode
    0.71
    merce
    0.70
    Activations Density 0.269%

    No Known Activations