© 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. 7848
    Prev
    Next
    INDEX
    Explanations

    questions or statements posing inquiries

    oai_token-act-pair · gpt-3.5-turbo

    questions posed in the text

    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
    ventures
    -0.76
    "},"
    -0.69
    itches
    -0.65
    urous
    -0.65
    CBC
    -0.63
     parap
    -0.62
    ucl
    -0.59
    Late
    -0.56
     UCH
    -0.55
    reau
    -0.55
    POSITIVE LOGITS
     whether
    1.34
     why
    1.14
     how
    1.12
     WHY
    1.07
    whether
    1.01
     moot
    0.88
    why
    0.85
     what
    0.83
     whats
    0.80
     unanswered
    0.79
    Activations Density 0.066%

    No Known Activations