© 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 · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14611
    Prev
    Next
    INDEX
    Explanations

    information related to political elections, candidates, votes and percentages

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1055
    +0.10
    0.3%
    609
    +0.09
    0.3%
    453
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1770
    +0.10
    0.04
    81
    +0.09
    0.03
    647
    +0.09
    0.03
    Negative Logits
     tricot
    -0.56
    <bos>
    -0.50
    pushd
    -0.50
    fputs
    -0.48
     worin
    -0.48
    erapeu
    -0.47
     worauf
    -0.44
     womit
    -0.43
    glMatrixMode
    -0.42
    ഒ
    -0.41
    POSITIVE LOGITS
     votes
    0.73
     kompati
    0.63
     ballots
    0.62
     panik
    0.62
     vote
    0.62
    votes
    0.61
     silikon
    0.61
    Votes
    0.59
     Votes
    0.59
     akut
    0.58
    Activations Density 0.314%

    No Known Activations