© 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. 8-RES-JB
    11. 1046
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon, potentially related to coding or gaming

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific descriptors and qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Synopsis
    -0.63
    cosystem
    -0.62
    QUIRE
    -0.61
     Parish
    -0.60
    pires
    -0.57
    etsy
    -0.56
    MENTS
    -0.56
    udeb
    -0.54
    sylv
    -0.54
    aminer
    -0.54
    POSITIVE LOGITS
     versus
    0.78
     vs
    0.71
    boxing
    0.70
    -,
    0.67
     realism
    0.66
    paren
    0.65
    !".
    0.62
     pudding
    0.62
    !,
    0.62
     neutrality
    0.61
    Activations Density 0.686%

    No Known Activations