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. 7769
    Prev
    Next
    INDEX
    Explanations

    references to collective action and responsibility

    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
    +0.41
    1.5%
    1919
    +0.11
    0.4%
    1510
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.41
    0.18
    1415
    +0.11
    0.10
    1510
    +0.09
    0.07
    Negative Logits
    <bos>
    -2.25
     gend
    -0.86
     adal
    -0.81
     vang
    -0.80
     gie
    -0.79
     glan
    -0.78
     frans
    -0.78
     ù
    -0.77
     puc
    -0.75
     hej
    -0.72
    POSITIVE LOGITS
     should
    1.03
     shouldn
    0.98
     soulign
    0.96
     Should
    0.93
     Shouldn
    0.93
     véhic
    0.93
     tupperware
    0.92
     ought
    0.89
    Should
    0.87
     need
    0.86
    Activations Density 0.821%

    No Known Activations