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. 3
    Prev
    Next
    INDEX
    Explanations

    phrases related to activities, especially sports and performances

    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
    +0.08
    0.3%
    783
    +0.06
    0.2%
    1074
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.08
    0.04
    371
    +0.06
    0.04
    1675
    +0.05
    0.04
    Negative Logits
    <bos>
    -1.26
    public
    -0.82
    ⓧ
    -0.77
    void
    -0.77
    if
    -0.77
    const
    -0.76
    ///**
    -0.76
    //{
    
    -0.75
    private
    -0.75
    return
    -0.75
    POSITIVE LOGITS
     affor
    2.77
     maneu
    2.72
     increa
    2.63
     accla
    2.50
     impra
    2.44
     excru
    2.41
     guarante
    2.40
     reluct
    2.40
     fuf
    2.40
     wherea
    2.38
    Activations Density 0.179%

    No Known Activations