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. 15088
    Prev
    Next
    INDEX
    Explanations

    information related to historical events and biographical details of individuals, potentially with a focus on specific organizations or foundations

    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
    394
    +0.15
    0.5%
    1699
    +0.13
    0.4%
    2034
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1843
    +0.15
    0.03
    764
    +0.13
    0.04
    394
    +0.13
    0.04
    Negative Logits
     dichi
    -0.85
    źródło
    -0.82
    Ótimo
    -0.79
    Ży
    -0.79
     voleva
    -0.78
    Dziękuję
    -0.78
    Przyp
    -0.77
    troppo
    -0.75
     Muitos
    -0.75
    Pued
    -0.75
    POSITIVE LOGITS
    </h2>
    0.70
    </h3>
    0.67
     Undoubtedly
    0.67
    ↵↵
    0.67
    </h1>
    0.65
    :
    0.63
    </strong>
    0.62
     Whilst
    0.61
    ↵
    0.60
    </h4>
    0.60
    Activations Density 0.336%

    No Known Activations