Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 21053
    Prev
    Next
    INDEX
    Explanations

    references to the politician Mitt Romney

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Mitt Romney

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.74
     DRAG
    -0.74
    SHIP
    -0.73
    */(
    -0.72
    ĨĴ
    -0.71
    istence
    -0.67
    netflix
    -0.66
    FUL
    -0.66
     beet
    -0.65
    Ô
    -0.65
    POSITIVE LOGITS
     Romney
    1.44
    Romney
    1.10
     Mitt
    0.97
    erer
    0.87
    ens
    0.83
    sburgh
    0.83
    rod
    0.82
    ani
    0.79
     Santorum
    0.79
    erers
    0.79
    Activations Density 0.014%

    No Known Activations