© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 2775
    Prev
    Next
    INDEX
    Explanations

    numbers related to election votes

    oai_token-act-pair · gpt-3.5-turbo

    references to voting results or electoral outcomes

    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
    Else
    -0.78
    eton
    -0.76
     millenn
    -0.75
     unden
    -0.74
    obar
    -0.74
     antioxid
    -0.72
     thous
    -0.70
    TIT
    -0.70
    Nap
    -0.69
    £ı
    -0.69
    POSITIVE LOGITS
     votes
    1.18
    vote
    1.10
     vote
    1.03
     Vote
    1.00
     ballots
    0.99
     Votes
    0.99
     voting
    0.86
    votes
    0.86
     Voting
    0.85
    itters
    0.78
    Activations Density 0.017%

    No Known Activations