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. 10-RES-JB
    6. 6860
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "still" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.25
    1.3%
    481
    +0.13
    0.7%
    1671
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.25
    0.06
    122
    +0.13
    0.06
    577
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.64
    glColor
    -0.65
    <!--[
    -0.64
    }{||
    -0.61
    ोंने
    -0.60
    //});
    -0.60
    br
    -0.59
    Array
    -0.59
     thiệu
    -0.58
    archive
    -0.58
    POSITIVE LOGITS
     maneu
    1.74
     impra
    1.62
     practition
    1.61
     affor
    1.60
     lidl
    1.60
     stockholm
    1.60
     Juf
    1.59
     milf
    1.58
     unden
    1.57
     bordeaux
    1.57
    Activations Density 0.091%

    No Known Activations