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. 1442
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or entities in the context of competitions or games

    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
    184
    +0.20
    0.6%
    964
    +0.17
    0.6%
    1343
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.20
    0.03
    184
    +0.17
    0.01
    964
    +0.16
    0.02
    Negative Logits
    ьаж
    -0.79
     kasarigan
    -0.62
    RTSN
    -0.61
     Campionato
    -0.58
     Rumuni
    -0.56
     parlando
    -0.56
    OCCURRED
    -0.55
    Espèce
    -0.55
     abito
    -0.52
    gemeente
    -0.52
    POSITIVE LOGITS
    InjectAttribute
    0.45
     >=",
    0.42
     houver
    0.42
     inkább
    0.42
    LMAO
    0.41
    Aiheesta
    0.40
    Lmao
    0.40
     Applicability
    0.39
    Jeez
    0.39
     PyTuple
    0.39
    Activations Density 0.088%

    No Known Activations