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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 812
    Prev
    Next
    INDEX
    Explanations

    mentions of competition and winning in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.14
    0.7%
    1978
    +0.14
    0.7%
    764
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.14
    0.04
    1042
    +0.14
    0.04
    1036
    +0.14
    0.02
    Negative Logits
    <bos>
    -3.34
     Administrativna
    -0.76
    Panamoan
    -0.75
    новништво
    -0.74
     Italijanski
    -0.65
    thâu
    -0.63
    Jeografia
    -0.60
     становника
    -0.60
     ModelExpression
    -0.58
    bewerken
    -0.58
    POSITIVE LOGITS
     impra
    1.12
     disreg
    1.11
     viciss
    1.09
     accla
    1.08
     sappi
    1.07
     impractica
    1.05
     unwarran
    1.04
     maneu
    1.04
     indestru
    1.04
     ecru
    1.03
    Activations Density 0.610%

    No Known Activations