© 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. 11497
    Prev
    Next
    INDEX
    Explanations

    phrases indicating unexpected or revealing information

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "it turns out."

    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
    è¦ļéĨĴ
    -0.82
    rongh
    -0.61
    rak
    -0.60
     registry
    -0.54
    accompan
    -0.54
     recre
    -0.53
    going
    -0.53
     confir
    -0.52
     Zan
    -0.52
     disqualified
    -0.52
    POSITIVE LOGITS
     out
    0.71
    baugh
    0.64
    Thumbnail
    0.63
    NRS
    0.61
    ilege
    0.60
    enum
    0.59
    entious
    0.59
    gly
    0.57
    arb
    0.57
    outs
    0.57
    Activations Density 0.021%

    No Known Activations