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. 6790
    Prev
    Next
    INDEX
    Explanations

    instructions related to tasks involving cutting or assembling items

    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
    +0.28
    1.2%
    1013
    +0.22
    1.0%
    381
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.28
    0.16
    736
    +0.22
    0.12
    1539
    +0.17
    0.04
    Negative Logits
    <bos>
    -2.63
    Geplaatst
    -0.81
    public
    -0.78
    CreateMap
    -0.72
     Himo
    -0.70
     Italijani
    -0.69
    HasIndex
    -0.69
    IsContent
    -0.69
    Referències
    -0.68
    /**
    
    -0.68
    POSITIVE LOGITS
     shenan
    2.18
     impra
    2.17
     maneu
    2.14
     reluct
    2.08
     disagre
    1.97
     unspeak
    1.92
     accla
    1.92
     disgra
    1.91
     disreg
    1.88
     apprehen
    1.86
    Activations Density 2.374%

    No Known Activations