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. 19394
    Prev
    Next
    INDEX
    Explanations

    mentions of specific political figures like President Obama

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures, particularly Barack Obama and Donald Trump

    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
    MJ
    -0.77
    Offline
    -0.72
    NP
    -0.66
     mats
    -0.65
    ãĤ¯
    -0.64
     notebooks
    -0.64
     dates
    -0.64
    Tokens
    -0.64
     probabilities
    -0.61
    coins
    -0.61
    POSITIVE LOGITS
    ÃŃs
    0.88
     vetoed
    0.80
     Presents
    0.78
     Jinping
    0.76
     assembled
    0.75
     pard
    0.72
    iets
    0.69
    hower
    0.68
    enstein
    0.68
     Appears
    0.68
    Activations Density 0.062%

    No Known Activations