© 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. 3357
    Prev
    Next
    INDEX
    Explanations

    information related to potentially hazardous substances and chemicals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to carcinogenic substances and environmental hazards

    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
     unification
    -0.85
    issance
    -0.81
     Fellowship
    -0.79
    Kings
    -0.78
     pivot
    -0.77
    joy
    -0.76
     reunion
    -0.74
    ospels
    -0.73
    iku
    -0.71
    plom
    -0.69
    POSITIVE LOGITS
     contaminants
    1.67
     contamin
    1.54
     contamination
    1.47
     contaminated
    1.46
     chemicals
    1.41
     additives
    1.38
     ammonia
    1.36
     toxins
    1.32
     pollutants
    1.30
     substances
    1.23
    Activations Density 0.502%

    No Known Activations