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. 121
    Prev
    Next
    INDEX
    Explanations

    concepts related to creativity and imaginative thoughts

    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
    +0.28
    0.9%
    906
    +0.11
    0.3%
    631
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1317
    +0.28
    0.04
    1746
    +0.11
    0.06
    1446
    +0.07
    0.05
    Negative Logits
     intersper
    -1.58
     shenan
    -1.48
     encomp
    -1.45
     depic
    -1.44
     apprehen
    -1.38
     indestru
    -1.29
     disagre
    -1.28
     unspeak
    -1.25
    <bos>
    -1.24
     increa
    -1.22
    POSITIVE LOGITS
     pyplot
    0.80
    InjectMocks
    0.79
    yticks
    0.77
     thoughts
    0.75
    />";
    0.74
     AssemblyCulture
    0.71
     luat
    0.70
    xtick
    0.70
    xticks
    0.68
    Tē
    0.68
    Activations Density 0.757%

    No Known Activations