Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 14986
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical activities or exercises

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    0.9%
    738
    +0.12
    0.5%
    1013
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.23
    0.12
    694
    +0.12
    0.07
    1336
    +0.10
    0.09
    Negative Logits
    <bos>
    -3.16
    public
    -0.71
    ///**
    -0.70
    ⓧ
    -0.70
    echo
    -0.67
    abspath
    -0.66
    HasIndex
    -0.66
    prop
    -0.65
     AppCompatTheme
    -0.65
    def
    -0.65
    POSITIVE LOGITS
     Minang
    1.97
     lele
    1.91
     Keny
    1.81
     maneu
    1.79
     hcm
    1.78
     bandung
    1.77
     fortn
    1.77
     suspic
    1.75
     Juf
    1.74
     fta
    1.73
    Activations Density 2.024%

    No Known Activations