© 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. 11-RES-JB
    11. 1868
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant event or situation followed by a subsequent reaction or development

    oai_token-act-pair · gpt-3.5-turbo

    references to events or situations following significant incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jab
    -0.62
    redited
    -0.62
    urat
    -0.61
    inates
    -0.58
    abo
    -0.56
    limit
    -0.55
    afort
    -0.55
    reated
    -0.55
     forbidden
    -0.54
    isible
    -0.54
    POSITIVE LOGITS
     of
    0.99
     thereof
    0.93
     largeDownload
    0.73
    ebin
    0.72
    math
    0.70
     Hurricane
    0.69
    ricane
    0.69
     aftermath
    0.68
    Charl
    0.67
     revelations
    0.67
    Activations Density 0.073%

    No Known Activations