© 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. 1962
    Prev
    Next
    INDEX
    Explanations

    health-related risks and associations with specific behaviors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health risks and associated factors

    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
    issance
    -0.85
     Dick
    -0.69
    åħī
    -0.67
    utra
    -0.67
    SEC
    -0.67
    orld
    -0.66
    atom
    -0.63
    Dick
    -0.62
    cious
    -0.62
     Plex
    -0.62
    POSITIVE LOGITS
     allele
    0.94
     factors
    0.86
    busters
    0.77
    ogenic
    0.76
     (%)
    0.76
     predis
    0.76
     factor
    0.75
     behaviours
    0.75
     behaviors
    0.74
     obesity
    0.74
    Activations Density 0.083%

    No Known Activations