© 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. 1060
    Prev
    Next
    INDEX
    Explanations

    numerical expressions like fractions and percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data or metrics

    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
    natureconservancy
    -0.67
     PUBLIC
    -0.61
     Anthropology
    -0.57
     familiar
    -0.56
     Wilde
    -0.56
     Artemis
    -0.56
     Akin
    -0.56
    grave
    -0.55
    Dialogue
    -0.55
     Corrections
    -0.54
    POSITIVE LOGITS
    ousand
    1.03
    otted
    0.98
    velength
    0.95
    perature
    0.91
    undred
    0.89
    opter
    0.89
    pped
    0.84
    enger
    0.84
    anded
    0.83
    pect
    0.83
    Activations Density 0.127%

    No Known Activations