© 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. 0-RES-JB
    11. 18863
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "SR" with high activation

    oai_token-act-pair · gpt-3.5-turbo

    references to specific medical terms and assessments related to health metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feast
    -0.75
     bust
    -0.71
     Bend
    -0.69
     Bed
    -0.69
     Olymp
    -0.68
     Flowers
    -0.66
    imet
    -0.66
     sting
    -0.66
     Ghana
    -0.65
     appl
    -0.65
    POSITIVE LOGITS
    SR
    4.03
     SR
    2.83
    sr
    1.76
     sr
    1.63
    LR
    1.62
    JR
    1.37
    RP
    1.32
     LR
    1.30
    CR
    1.20
     JR
    1.18
    Activations Density 0.017%

    No Known Activations