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. 22075
    Prev
    Next
    INDEX
    Explanations

    mentions of political nominees

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political candidacy and nomination status

    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
    ioch
    -0.94
    chrom
    -0.80
    rael
    -0.80
    OTO
    -0.79
    orem
    -0.79
    phis
    -0.79
    alam
    -0.78
    azel
    -0.77
    onal
    -0.75
     gou
    -0.75
    POSITIVE LOGITS
     presumptive
    1.29
     frontrunner
    0.96
     presidential
    0.84
     nominee
    0.81
     impeachment
    0.81
     nominees
    0.79
     Donald
    0.79
    ptive
    0.79
     Trump
    0.76
     Hillary
    0.73
    Activations Density 0.008%

    No Known Activations