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. 13549
    Prev
    Next
    INDEX
    Explanations

    documents or descriptions related to creating and using software programs, especially involving games or technology applications

    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
    1124
    +0.17
    0.6%
    1150
    +0.13
    0.5%
    1624
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1124
    +0.17
    0.05
    1993
    +0.13
    0.04
    1624
    +0.13
    0.03
    Negative Logits
    جوايز
    -0.55
    PDOException
    -0.48
    Để
    -0.47
    bạn
    -0.47
    imdi
    -0.47
    cimientos
    -0.46
    gameserver
    -0.46
    quarter
    -0.46
    cieron
    -0.45
     kwietnia
    -0.45
    POSITIVE LOGITS
     vété
    0.93
     fameux
    0.90
     affez
    0.89
     habile
    0.86
     USING
    0.86
     péné
    0.86
     épu
    0.85
     usine
    0.84
     malheureux
    0.84
     délib
    0.84
    Activations Density 0.103%

    No Known Activations