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. 5283
    Prev
    Next
    INDEX
    Explanations

    mentions of political seats

    oai_token-act-pair · gpt-3.5-turbo

    references to political positions or electoral seats

    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
    DragonMagazine
    -0.76
     Turtles
    -0.75
    ocrine
    -0.71
     Entertainment
    -0.69
    sonian
    -0.69
    STD
    -0.67
    onut
    -0.65
    ODUCT
    -0.64
    obyl
    -0.64
    icol
    -0.64
    POSITIVE LOGITS
    holders
    1.14
    holder
    1.13
    seat
    1.04
    belt
    0.98
     seat
    0.95
    mate
    0.93
     vacated
    0.92
    vote
    0.91
     holders
    0.91
    mates
    0.90
    Activations Density 0.016%

    No Known Activations