Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 7773
    Prev
    Next
    INDEX
    Explanations

    mentions of specific authors or literary figures, primarily J.R.R. Tolkien

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.15
    0.5%
    50
    +0.14
    0.5%
    1597
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.15
    0.06
    283
    +0.14
    0.02
    1597
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.59
    ScopeManager
    -0.70
     come
    -0.65
     came
    -0.62
     must
    -0.61
     coming
    -0.61
     make
    -0.60
    гӀ
    -0.60
    0
    -0.60
     do
    -0.60
    POSITIVE LOGITS
     Sén
    1.61
     Ottobre
    1.56
     Docteur
    1.54
     Messieurs
    1.50
     Février
    1.50
     Souha
    1.49
     Lég
    1.42
     Giugno
    1.42
     Settembre
    1.42
     Cfr
    1.42
    Activations Density 0.145%

    No Known Activations