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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12061
    Prev
    Next
    INDEX
    Explanations

    words related to tobacco and nicotine

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tobacco and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wynne
    -0.76
     Ake
    -0.72
     Defenders
    -0.70
     Lazarus
    -0.69
    infeld
    -0.69
    ithmetic
    -0.68
     Gamergate
    -0.68
    imov
    -0.65
    inosaur
    -0.65
    olon
    -0.65
    POSITIVE LOGITS
     cigarettes
    1.09
     smoking
    0.99
     smoke
    0.97
     cessation
    0.95
     cigarette
    0.93
    arette
    0.86
     smoked
    0.85
     tobacco
    0.85
     puff
    0.85
    cigarette
    0.82
    Activations Density 0.010%

    No Known Activations