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. 16035
    Prev
    Next
    INDEX
    Explanations

    references to sports injuries and athletes' comebacks

    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
    394
    +0.12
    0.4%
    344
    +0.12
    0.4%
    906
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.12
    0.12
    344
    +0.12
    0.05
    575
    +0.12
    0.07
    Negative Logits
     embodi
    -1.15
     anhyd
    -1.06
     pollut
    -1.06
     époux
    -0.99
     alberto
    -0.94
     NOO
    -0.92
     §.
    -0.90
     nephe
    -0.89
     effe
    -0.89
     Whence
    -0.88
    POSITIVE LOGITS
    <bos>
    0.89
     виправивши
    0.61
    tvguidetime
    0.58
    حياته
    0.56
    Искәрмәләр
    0.56
     teammates
    0.55
     الرياضيه
    0.52
     preseason
    0.51
     insuffisamment
    0.51
     fans
    0.50
    Activations Density 2.544%

    No Known Activations