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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13421
    Prev
    Next
    INDEX
    Explanations

    sporting event-related phrases

    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
    1499
    +0.11
    0.3%
    906
    +0.09
    0.3%
    994
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1441
    +0.11
    0.04
    1551
    +0.09
    0.03
    2043
    +0.09
    0.03
    Negative Logits
     Octobre
    -0.96
     Décembre
    -0.90
     Février
    -0.90
     Juillet
    -0.88
     affez
    -0.88
     Septembre
    -0.86
     vedo
    -0.84
     insegna
    -0.80
     chèvre
    -0.80
     vogli
    -0.76
    POSITIVE LOGITS
     finals
    0.71
     semifinals
    0.69
     semifinal
    0.60
     finalists
    0.58
     quarterfinals
    0.58
     playoffs
    0.56
     finalist
    0.56
    finals
    0.54
     Finals
    0.53
     McLaugh
    0.53
    Activations Density 0.156%

    No Known Activations