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. 1498
    Prev
    Next
    INDEX
    Explanations

    statements related to political parties, candidates, and elections

    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
    81
    +0.10
    0.3%
    599
    +0.08
    0.2%
    344
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.10
    0.04
    1551
    +0.08
    0.04
    416
    +0.07
    0.04
    Negative Logits
     unlaw
    -0.95
     liberality
    -0.93
     impractica
    -0.90
     pymysql
    -0.83
     anhyd
    -0.79
     unwarran
    -0.77
     felicity
    -0.76
     psycopg
    -0.76
     pollut
    -0.76
     glau
    -0.75
    POSITIVE LOGITS
     Demokrat
    0.61
     Democratic
    0.58
     party
    0.58
     nomination
    0.57
     praktik
    0.51
     manuten
    0.49
     nominations
    0.49
     candidates
    0.49
     Democrats
    0.49
     Party
    0.48
    Activations Density 0.310%

    No Known Activations