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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15198
    Prev
    Next
    INDEX
    Explanations

    information related to swimming and pools

    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
    +0.16
    0.8%
    1065
    +0.10
    0.5%
    1256
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1256
    +0.16
    0.03
    1768
    +0.10
    0.03
    1467
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.88
    ⓧ
    -0.77
     do
    -0.77
    HasColumnType
    -0.76
     AssemblyCompany
    -0.74
    var
    -0.73
    /*
    -0.71
    else
    -0.71
     des
    -0.71
    let
    -0.69
    POSITIVE LOGITS
     maneu
    2.00
     impra
    1.98
     increa
    1.97
     eiffel
    1.96
     bordeaux
    1.95
     stockholm
    1.95
     swarovski
    1.93
     affor
    1.90
     lidl
    1.87
     reluct
    1.85
    Activations Density 0.106%

    No Known Activations