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. 2482
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement or action

    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
    +0.21
    1.3%
    1562
    +0.14
    0.8%
    662
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1562
    +0.21
    0.12
    662
    +0.14
    0.09
    405
    +0.09
    0.09
    Negative Logits
    <bos>
    -3.41
     AssemblyCompany
    -0.73
    Kontrola
    -0.64
    public
    -0.64
    Portály
    -0.63
    getClassLoader
    -0.63
    //
    -0.62
     onCancelled
    -0.62
    setTotal
    -0.62
    भार
    -0.62
    POSITIVE LOGITS
     stockholm
    1.67
     getty
    1.63
     impra
    1.60
     unwarran
    1.60
     increa
    1.56
     véhic
    1.45
     volunte
    1.45
     maneu
    1.44
     opport
    1.44
     accla
    1.44
    Activations Density 0.283%

    No Known Activations