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 · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 673
    Prev
    Next
    INDEX
    Explanations

    references to political processes and decision-making, specifically related to referendums

    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
    1896
    +0.13
    0.4%
    1921
    +0.13
    0.4%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.13
    0.02
    1499
    +0.13
    0.02
    1492
    +0.10
    0.02
    Negative Logits
     solidar
    -0.71
     stiller
    -0.66
     utop
    -0.66
     impon
    -0.65
     compil
    -0.64
     glan
    -0.62
     kram
    -0.60
     stoff
    -0.60
     lomb
    -0.59
     meis
    -0.59
    POSITIVE LOGITS
     referendum
    1.18
     voters
    0.58
     vote
    0.57
     Voters
    0.56
     electorate
    0.56
     gruesa
    0.56
     ballots
    0.56
     ballot
    0.55
     Silurian
    0.53
     voter
    0.52
    Activations Density 0.082%

    No Known Activations