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. 595
    Prev
    Next
    INDEX
    Explanations

    JavaScript functions related to setting Frames Per Second (FPS) in a game or animation

    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
    453
    +0.10
    0.3%
    876
    +0.10
    0.3%
    184
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.10
    0.02
    1774
    +0.10
    0.01
    1831
    +0.09
    0.01
    Negative Logits
     apprehen
    -0.96
     unspeak
    -0.96
     exé
    -0.94
     gaily
    -0.90
     vainly
    -0.89
     quitted
    -0.89
     Juf
    -0.85
     envoie
    -0.84
     philanth
    -0.81
     ferait
    -0.81
    POSITIVE LOGITS
    rehensive
    0.78
     Himo
    0.72
     hornblende
    0.71
     plagioclase
    0.71
     tetrach
    0.70
     feldspar
    0.69
     NKC
    0.69
     zirc
    0.68
     Btu
    0.68
    seded
    0.67
    Activations Density 0.032%

    No Known Activations