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. 2-RES-JB
    6. 333
    Prev
    Next
    INDEX
    Explanations

    terms related to the voting process and ballot counting

    oai_token-act-pair · gpt-4-turbo

    numbers related to voting and election results

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to voting and election processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.93
    ĨĴ
    -0.77
     dependency
    -0.71
    ETA
    -0.69
    ifestyle
    -0.68
    depend
    -0.65
     mercenary
    -0.65
    thur
    -0.64
     culinary
    -0.64
     Cargo
    -0.62
    POSITIVE LOGITS
    vote
    1.14
     ballots
    1.09
     Elections
    1.07
     Vote
    1.05
    eering
    1.01
     votes
    1.00
     Voting
    0.99
     vote
    0.99
     voter
    0.97
     Voter
    0.97
    Activations Density 0.397%

    No Known Activations