© 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. 8-RES-JB
    11. 23906
    Prev
    Next
    INDEX
    Explanations

    phrases indicating alternatives or different perspectives

    oai_token-act-pair · gpt-3.5-turbo

    discussions about choices, paths, or dualities within societal or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVERS
    -0.73
    د
    -0.67
    س
    -0.63
    details
    -0.62
    DERR
    -0.62
    zos
    -0.62
    sbm
    -0.61
    DJ
    -0.61
    ende
    -0.59
    actionDate
    -0.59
    POSITIVE LOGITS
     apiece
    0.91
    ilion
    0.78
    undred
    0.64
     lobe
    0.64
     stroke
    0.63
     altogether
    0.61
     individually
    0.61
     equals
    0.60
     versus
    0.60
     increments
    0.60
    Activations Density 0.108%

    No Known Activations