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. 306
    Prev
    Next
    INDEX
    Explanations

    situations where someone is criticizing or addressing others in a confrontational manner

    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
    50
    +0.10
    0.3%
    1741
    +0.09
    0.3%
    1042
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.10
    0.04
    16
    +0.09
    0.04
    1820
    +0.09
    0.03
    Negative Logits
     levier
    -0.75
     habang
    -0.74
     McInt
    -0.71
     kasama
    -0.69
     vêtement
    -0.68
     investissement
    -0.66
     plongée
    -0.66
     déplo
    -0.65
     fantaisie
    -0.64
     oeil
    -0.64
    POSITIVE LOGITS
     minuta
    0.85
     tramont
    0.77
     doman
    0.76
     provence
    0.75
     noce
    0.70
     caché
    0.68
     dises
    0.68
     patin
    0.67
     fras
    0.67
     palio
    0.67
    Activations Density 0.185%

    No Known Activations