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. 1874
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a gentle or mild approach

    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
    +0.20
    0.7%
    75
    +0.10
    0.3%
    1035
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.20
    0.05
    277
    +0.10
    0.03
    814
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.47
     intersper
    -1.41
     wherea
    -1.08
     unve
    -0.98
     endow
    -0.98
     fuf
    -0.97
     embra
    -0.97
     inappro
    -0.96
     unlaw
    -0.94
     campa
    -0.94
    POSITIVE LOGITS
     Bardzo
    0.69
     Muito
    0.69
    slidesPer
    0.65
    číta
    0.64
     Talvez
    0.63
    cupertino
    0.61
    OBJETIVO
    0.61
     prieten
    0.60
    borderTop
    0.58
    viewWillAppear
    0.58
    Activations Density 0.247%

    No Known Activations