© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 20869
    Prev
    Next
    INDEX
    Explanations

    information related to news articles or reports about various political and social subjects

    oai_token-act-pair · gpt-3.5-turbo

    punctuated segments of text that list items or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quist
    -0.78
    uce
    -0.76
    inx
    -0.76
    iple
    -0.76
    anish
    -0.73
    uble
    -0.72
    earch
    -0.72
    ocry
    -0.71
    ances
    -0.71
    orne
    -0.70
    POSITIVE LOGITS
     namely
    1.41
     albeit
    0.93
     Spectre
    0.87
     respectively
    0.84
     which
    0.79
     viz
    0.78
     aptly
    0.74
     called
    0.74
     Watt
    0.73
     thereby
    0.73
    Activations Density 0.317%

    No Known Activations