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. 8343
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific game mechanics or rules, possibly related to strategy or instructions

    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
    281
    +0.16
    0.7%
    1059
    +0.14
    0.6%
    528
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.16
    0.04
    1059
    +0.14
    0.04
    528
    +0.14
    0.03
    Negative Logits
    timbangan
    -0.54
     zobaczyć
    -0.46
    NamedQueries
    -0.46
    SneakyThrows
    -0.45
    secuted
    -0.45
     initComponents
    -0.45
    CDCl
    -0.45
    Bagaimana
    -0.44
     zostać
    -0.44
    enaam
    -0.44
    POSITIVE LOGITS
     PER
    1.14
     Per
    1.13
    Per
    1.08
     exé
    1.05
     permu
    0.99
    per
    0.99
     rempliss
    0.97
     perpé
    0.96
     Persi
    0.96
     Ename
    0.94
    Activations Density 0.117%

    No Known Activations