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. 1260
    Prev
    Next
    INDEX
    Explanations

    references to injuries and medical issues in sports-related contexts

    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
    964
    +0.09
    0.3%
    495
    +0.08
    0.2%
    218
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    619
    +0.09
    0.02
    495
    +0.08
    0.03
    1449
    +0.07
    0.01
    Negative Logits
     frambo
    -0.61
     ananas
    -0.60
    SBATCH
    -0.56
     marte
    -0.56
     aquare
    -0.55
    ükemmel
    -0.54
     herbes
    -0.53
     grotte
    -0.52
     stiller
    -0.52
     svin
    -0.52
    POSITIVE LOGITS
     gaily
    0.71
     vainly
    0.70
     previously
    0.67
     thrived
    0.67
     originally
    0.65
     formerly
    0.63
     quitted
    0.63
     ineffec
    0.62
     vanished
    0.61
     contribut
    0.59
    Activations Density 0.590%

    No Known Activations