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. 15449
    Prev
    Next
    INDEX
    Explanations

    specific names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures associated with a resignation or controversy

    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
     Minotaur
    -0.80
     Jericho
    -0.73
    omas
    -0.73
     Viking
    -0.71
    otropic
    -0.69
    olithic
    -0.69
     Gemini
    -0.66
    istically
    -0.65
    odus
    -0.63
    orate
    -0.62
    POSITIVE LOGITS
     Wasserman
    1.16
     Schultz
    1.05
    ignt
    0.84
    wcs
    0.77
    engers
    0.71
    etti
    0.71
     Tanz
    0.71
    Leaks
    0.71
    staff
    0.70
    urations
    0.69
    Activations Density 0.017%

    No Known Activations