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. 10155
    Prev
    Next
    INDEX
    Explanations

    mentions of legendary or mythical figures, stories, or concepts

    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
    1034
    +0.14
    0.5%
    1437
    +0.11
    0.4%
    200
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1516
    +0.14
    0.02
    1034
    +0.11
    0.03
    2030
    +0.11
    0.02
    Negative Logits
    ValueGeneration
    -0.59
    Referencie
    -0.59
     تضيفلها
    -0.59
    Šaltiniai
    -0.58
     pà
    -0.56
     nawr
    -0.53
    DropColumn
    -0.52
    garmin
    -0.51
    kezi
    -0.48
     Tarjeta
    -0.48
    POSITIVE LOGITS
    legend
    1.10
     legend
    1.09
     myth
    1.04
     myths
    0.98
     LEGEND
    0.95
     Legend
    0.95
     legends
    0.95
    Legend
    0.89
     Myth
    0.88
    Myth
    0.85
    Activations Density 0.078%

    No Known Activations