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. 990
    Prev
    Next
    INDEX
    Explanations

    specific terms and concepts related to integrity and its implications in 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
    1.0%
    1978
    +0.18
    0.7%
    1842
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.25
    0.12
    1978
    +0.18
    0.11
    455
    +0.10
    0.07
    Negative Logits
    <bos>
    -2.20
    .
    -0.78
     gero
    -0.71
    ;
    -0.71
     bü
    -0.69
     beton
    -0.66
     tré
    -0.66
     respekt
    -0.66
     plak
    -0.65
     elek
    -0.65
    POSITIVE LOGITS
     unwarran
    1.68
     affor
    1.54
     chrysler
    1.41
     tolerably
    1.41
     tucson
    1.40
     véhic
    1.37
     unlaw
    1.37
     impra
    1.36
     disagre
    1.35
     🤣🤣
    1.33
    Activations Density 1.392%

    No Known Activations