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. 0-RES-JB
    6. 7
    Prev
    Next
    INDEX
    Explanations

    descriptions of personal information related to individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.12
    0.5%
    1059
    +0.06
    0.3%
    1828
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1059
    +0.12
    0.04
    1769
    +0.06
    0.04
    792
    +0.06
    0.04
    Negative Logits
    <bos>
    -1.71
    public
    -0.82
    //
    -0.70
     put
    -0.69
    /*
    -0.69
    }{||
    -0.68
    </tbody>
    -0.67
    export
    -0.67
    const
    -0.67
    struct
    -0.66
    POSITIVE LOGITS
     maneu
    2.04
     affor
    1.96
     stockholm
    1.95
     lidl
    1.88
     increa
    1.83
     accla
    1.81
     disagre
    1.79
     embodi
    1.78
     effe
    1.78
     age
    1.77
    Activations Density 0.112%

    No Known Activations