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. 12-RES-JB
    6. 176
    Prev
    Next
    INDEX
    Explanations

    statistical metrics related to team performance in sports

    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.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.28
    1.0%
    1150
    +0.13
    0.5%
    382
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.28
    0.08
    1978
    +0.13
    0.08
    1013
    +0.12
    0.07
    Negative Logits
    <bos>
    -1.74
     encre
    -1.17
     succede
    -1.15
     solidar
    -1.13
     dispen
    -1.08
     Ottobre
    -1.05
     piú
    -1.05
     abr
    -1.05
     voleva
    -1.02
     parteci
    -1.01
    POSITIVE LOGITS
    .
    0.90
    ;
    0.74
     ErrorCode
    0.72
    ,
    0.70
     stuks
    0.69
     BigNumber
    0.69
     (
    0.69
    0
    0.68
    。
    0.67
    başı
    0.66
    Activations Density 0.458%

    No Known Activations