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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1474
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports performance

    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
    1842
    +0.10
    0.3%
    1819
    +0.10
    0.3%
    1870
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    833
    +0.10
    0.04
    1819
    +0.10
    0.04
    2020
    +0.09
    0.04
    Negative Logits
     immen
    -1.02
     bont
    -0.99
     kram
    -0.99
     ciga
    -0.98
     socie
    -0.97
     affez
    -0.97
     Lombar
    -0.96
     dispen
    -0.95
     notor
    -0.94
     lapto
    -0.94
    POSITIVE LOGITS
     while
    0.53
     total
    0.52
     strikeouts
    0.49
     assists
    0.49
     during
    0.49
     rheumatism
    0.49
     per
    0.47
     teammate
    0.47
     touchdowns
    0.47
     teammates
    0.47
    Activations Density 0.151%

    No Known Activations