Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15040
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures, policy proposals, and legislative actions

    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
    764
    +0.24
    0.8%
    394
    +0.18
    0.6%
    137
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.24
    0.06
    764
    +0.18
    0.04
    184
    +0.16
    0.02
    Negative Logits
     pymysql
    -0.79
     LIRE
    -0.75
     carrefour
    -0.72
     velours
    -0.63
     paillettes
    -0.61
     porcelaine
    -0.60
     serai
    -0.59
    ഉ
    -0.58
     quai
    -0.58
     surpl
    -0.58
    POSITIVE LOGITS
     unve
    0.52
     pinulongan
    0.52
    BeginInit
    0.50
    <eos>
    0.49
     للمعارف
    0.48
    PMailer
    0.48
    商品説明
    0.48
    parsedMessage
    0.47
     Unclassified
    0.47
     stratigraph
    0.44
    Activations Density 0.359%

    No Known Activations