© 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. 6324
    Prev
    Next
    INDEX
    Explanations

    phrases referencing quotations or direct speech

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and brackets, indicating direct speech or citations

    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
     pitch
    -0.74
     radar
    -0.71
     shock
    -0.68
     panic
    -0.68
     reception
    -0.67
     prod
    -0.66
     photography
    -0.65
     luck
    -0.65
     turnover
    -0.65
     Radar
    -0.65
    POSITIVE LOGITS
    without
    1.75
    within
    1.68
    against
    1.65
    during
    1.56
    with
    1.55
    into
    1.54
    because
    1.50
    before
    1.49
    until
    1.47
    when
    1.47
    Activations Density 0.174%

    No Known Activations