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. 7782
    Prev
    Next
    INDEX
    Explanations

    prominent figures and their roles or contributions, particularly in political or sports contexts

    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
    +0.36
    1.5%
    1919
    +0.15
    0.6%
    1978
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.36
    0.17
    1097
    +0.15
    0.13
    1675
    +0.11
    0.10
    Negative Logits
    <bos>
    -1.99
     franz
    -1.22
     levis
    -1.21
     antik
    -1.16
     ù
    -1.16
     puc
    -1.16
     tsi
    -1.14
     permu
    -1.14
     fluo
    -1.13
     ordina
    -1.13
    POSITIVE LOGITS
     cannot
    0.82
     has
    0.82
     deserves
    0.81
     isn
    0.77
     seems
    0.75
    />";
    0.74
     is
    0.74
     will
    0.73
     may
    0.72
     hasn
    0.72
    Activations Density 1.095%

    No Known Activations