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. 7778
    Prev
    Next
    INDEX
    Explanations

    names and entities related to sports and entertainment figures

    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
    1177
    +0.22
    0.8%
    1842
    +0.14
    0.5%
    964
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1177
    +0.22
    0.05
    1741
    +0.14
    0.02
    283
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.73
    .
    -0.97
    <eos>
    -0.93
     and
    -0.92
    ,
    -0.90
     for
    -0.90
     in
    -0.90
     at
    -0.88
     on
    -0.88
     if
    -0.88
    POSITIVE LOGITS
     lele
    2.35
     alkoh
    2.33
     dises
    2.32
     kram
    2.31
     mef
    2.29
     cannes
    2.28
     wien
    2.28
     embra
    2.22
     stockholm
    2.22
     milano
    2.22
    Activations Density 0.768%

    No Known Activations