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. 8-RES-JB
    6. 6657
    Prev
    Next
    INDEX
    Explanations

    references to historical political figures, specifically focusing on Franklin Roosevelt

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Franklin" associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arine
    -0.90
    bour
    -0.87
    ming
    -0.86
    oided
    -0.86
    ynt
    -0.84
    bler
    -0.83
    rons
    -0.82
    ei
    -0.82
    HAEL
    -0.82
    ropolitan
    -0.82
    POSITIVE LOGITS
    ANCE
    0.88
    hurst
    0.75
     Roosevelt
    0.73
     Franklin
    0.71
     Contra
    0.66
    NL
    0.65
     shif
    0.65
    omaly
    0.64
    itiz
    0.63
     lim
    0.62
    Activations Density 0.046%

    No Known Activations