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. 1215
    Prev
    Next
    INDEX
    Explanations

    phrases related to psychological and health-related assessments

    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
    +0.27
    1.0%
    1842
    +0.23
    0.8%
    1150
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    897
    +0.27
    0.08
    752
    +0.23
    0.07
    1828
    +0.12
    0.07
    Negative Logits
    <bos>
    -2.80
    frastructure
    -0.72
    Datuak
    -0.69
    MessageOf
    -0.67
    EndProject
    -0.67
    
    
    -0.66
     ProtoMessage
    -0.64
     Walkover
    -0.61
    archiviato
    -0.61
     kaynağından
    -0.60
    POSITIVE LOGITS
     déchir
    0.58
     ladri
    0.57
     démarrage
    0.56
     grossa
    0.56
     bayern
    0.55
    '__
    0.54
     despi
    0.54
     Fakta
    0.53
     Teknik
    0.53
    =>'
    0.52
    Activations Density 0.977%

    No Known Activations