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. 734
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming, specifically focusing on damage calculations, skill actions, and enemy targeting mechanisms

    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
    +0.16
    0.5%
    1842
    +0.13
    0.4%
    736
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.16
    0.06
    74
    +0.13
    0.04
    93
    +0.11
    0.04
    Negative Logits
    UnitTesting
    -0.71
     silikon
    -0.70
     akut
    -0.69
     legislat
    -0.68
     praktik
    -0.68
    MessageOf
    -0.67
     biblia
    -0.67
     Jugos
    -0.65
     bakteri
    -0.65
     konserv
    -0.65
    POSITIVE LOGITS
     indestru
    0.97
    Noice
    0.93
     pymysql
    0.93
    Lma
    0.93
     hairc
    0.90
    FTFY
    0.90
     cushi
    0.89
     tupperware
    0.89
     swarovski
    0.88
     impractica
    0.88
    Activations Density 0.311%

    No Known Activations