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. 15318
    Prev
    Next
    INDEX
    Explanations

    baseball statistics and player performances

    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
    876
    +0.12
    0.4%
    1253
    +0.12
    0.4%
    184
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.12
    0.05
    736
    +0.12
    0.07
    1501
    +0.11
    0.04
    Negative Logits
     meis
    -0.82
     nomine
    -0.81
     Britann
    -0.78
     „,
    -0.77
     haer
    -0.76
     ecclesias
    -0.76
     Cæ
    -0.75
     wien
    -0.75
     onore
    -0.74
     maer
    -0.74
    POSITIVE LOGITS
    FTFY
    0.73
     averaged
    0.70
    Lmfao
    0.67
     prends
    0.66
    Lma
    0.64
     averages
    0.62
    YMMV
    0.62
    Noice
    0.62
    Hahah
    0.62
     average
    0.58
    Activations Density 0.485%

    No Known Activations