© 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. 1299
    Prev
    Next
    INDEX
    Explanations

    words related to marijuana, cannabis industry, and related medical and policy terms

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to industries and topics concerning health, regulations, and environmental issues

    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
    •single token firings
    Fires individually on " doping", " counterterrorism", " contraceptive", " DACA", also some sports

    No Comments

    Negative Logits
    anwhile
    -0.65
    urat
    -0.64
    theless
    -0.64
    ,,,,
    -0.60
    imately
    -0.60
    staking
    -0.60
    ciating
    -0.58
    iguous
    -0.57
    aline
    -0.57
    ulu
    -0.56
    POSITIVE LOGITS
     strategy
    0.74
     portfolio
    0.72
     programme
    0.72
     experience
    0.71
     program
    0.70
     initiative
    0.70
     empire
    0.69
     franchise
    0.69
     lineup
    0.68
     footprint
    0.67
    Activations Density 0.790%

    No Known Activations