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. 3-RES-JB
    6. 14552
    Prev
    Next
    INDEX
    Explanations

    words related to political or provocative rhetoric

    oai_token-act-pair · gpt-3.5-turbo

    words related to religion or spirituality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parenthood
    -0.80
    erate
    -0.71
    terday
    -0.70
     helic
    -0.66
    aeda
    -0.65
     jumper
    -0.64
    igned
    -0.63
    erves
    -0.62
    erial
    -0.62
    staking
    -0.62
    POSITIVE LOGITS
    glers
    1.19
    gers
    1.12
    glomer
    1.00
    lio
    1.00
    azine
    0.98
    reement
    0.96
    lia
    0.96
    allery
    0.94
    rils
    0.94
    roup
    0.91
    Activations Density 0.021%

    No Known Activations