Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7967
    Prev
    Next
    INDEX
    Explanations

    references to substances and substance abuse

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various substances and substance abuse topics

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

    No Comments

    Negative Logits
    DIR
    -0.73
    ITAL
    -0.67
    rium
    -0.66
     Hawks
    -0.66
    addafi
    -0.65
    ãĥ¼ãĤ¯
    -0.65
     Zimmer
    -0.65
    aldi
    -0.64
    kers
    -0.63
    ros
    -0.63
    POSITIVE LOGITS
     substances
    0.99
    fulness
    0.98
     substance
    0.93
    amphetamine
    0.89
     Substance
    0.89
    cohol
    0.87
    iveness
    0.85
     abusers
    0.85
     methamphetamine
    0.84
     abuser
    0.83
    Activations Density 0.010%

    No Known Activations