© 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. 14878
    Prev
    Next
    INDEX
    Explanations

    words related to achievements, results, or reactions with an emphasis on the positive

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with significant events or interactions in contexts such as relationships, responses, and performances

    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
     peas
    -0.75
     channels
    -0.72
     calcul
    -0.68
     diagrams
    -0.68
     charts
    -0.68
     chambers
    -0.67
     newsletters
    -0.67
     directions
    -0.62
    umbs
    -0.62
     branches
    -0.61
    POSITIVE LOGITS
    kick
    0.78
    pour
    0.77
    enegger
    0.76
    cko
    0.75
    enance
    0.75
    load
    0.75
     towards
    0.75
     ethic
    0.72
     compared
    0.71
     consisting
    0.71
    Activations Density 0.344%

    No Known Activations