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. 7874
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a problem or issue being overlooked or ignored

    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
    50
    +0.27
    0.9%
    1343
    +0.10
    0.3%
    1639
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1525
    +0.27
    0.04
    1171
    +0.10
    0.03
    533
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.64
     intersper
    -0.97
     apprehen
    -0.84
     disbur
    -0.79
     vainly
    -0.77
     attemp
    -0.75
     renounced
    -0.74
     lovel
    -0.74
     reconno
    -0.73
     interposed
    -0.72
    POSITIVE LOGITS
     soggior
    1.15
     cavallo
    1.02
     paillettes
    1.01
     bicic
    0.96
     cioc
    0.94
     ristor
    0.94
     broderie
    0.94
     palio
    0.93
     frambo
    0.92
     ویکی‌پدیای
    0.92
    Activations Density 0.565%

    No Known Activations