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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6881
    Prev
    Next
    INDEX
    Explanations

    mentions of significant actions or events in a sports context, particularly those related to scoring or leads in games

    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
    +0.22
    0.8%
    906
    +0.12
    0.4%
    1499
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    906
    +0.22
    0.01
    284
    +0.12
    0.03
    1833
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.70
     disbur
    -0.81
     hairc
    -0.80
    /**
    -0.76
     intersper
    -0.76
    ⓧ
    -0.76
     defray
    -0.73
     Stretcher
    -0.72
     quitted
    -0.72
     eyel
    -0.71
    POSITIVE LOGITS
     atualizado
    0.58
     كومونز
    0.56
     rainha
    0.56
     senhora
    0.55
     nguyen
    0.53
     Adicion
    0.53
     abstrato
    0.53
    SceneManagement
    0.52
     kado
    0.52
    memcmp
    0.51
    Activations Density 0.100%

    No Known Activations