© 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. 6446
    Prev
    Next
    INDEX
    Explanations

    words related to labeling, classifying, and designating things

    oai_token-act-pair · gpt-3.5-turbo

    terms related to classification and labeling

    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
     sqor
    -0.77
    umbn
    -0.73
    elin
    -0.64
    onse
    -0.63
    aptic
    -0.63
    andel
    -0.63
    edom
    -0.60
     intertw
    -0.59
     estimation
    -0.59
    ecd
    -0.59
    POSITIVE LOGITS
     as
    0.89
     accordingly
    0.82
    untarily
    0.74
    phas
    0.72
     unfit
    0.68
    IFIED
    0.64
     "#
    0.64
     "<
    0.63
     ineligible
    0.62
    ilingual
    0.62
    Activations Density 0.118%

    No Known Activations