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. 10114
    Prev
    Next
    INDEX
    Explanations

    words related to image processing, such as "JPEG", "soften", "sharp", "compositing", "pixels", and "logo"

    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
    +0.23
    0.7%
    678
    +0.11
    0.3%
    1823
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.23
    -0.01
    678
    +0.11
    0.04
    1446
    +0.09
    0.02
    Negative Logits
     Juventud
    -0.80
    <bos>
    -0.79
     Independencia
    -0.75
     Cár
    -0.65
     Valentín
    -0.65
     ویکی‌پدیای
    -0.64
     Asunción
    -0.64
     Irán
    -0.64
    Activité
    -0.63
    Père
    -0.62
    POSITIVE LOGITS
     disreg
    0.97
     uninten
    0.89
     thermomix
    0.88
     megane
    0.87
     encomp
    0.85
     increa
    0.84
     maneu
    0.84
     milano
    0.84
     embodi
    0.84
     scrat
    0.83
    Activations Density 0.344%

    No Known Activations