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. 906
    Prev
    Next
    INDEX
    Explanations

    phrases that denote relationships between individuals or entities

    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
    1.2%
    1343
    +0.15
    0.7%
    227
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.27
    0.05
    1930
    +0.15
    0.04
    227
    +0.13
    0.05
    Negative Logits
    <bos>
    -3.09
     expand
    -0.70
     to
    -0.70
     we
    -0.70
     introduce
    -0.69
     they
    -0.68
     hold
    -0.67
     let
    -0.67
     bring
    -0.66
     have
    -0.66
    POSITIVE LOGITS
     véhic
    1.65
     Juf
    1.61
     quoique
    1.53
     Keny
    1.53
     mikrofon
    1.51
     soulign
    1.50
     affor
    1.49
     Kategor
    1.49
     silikon
    1.49
     maksi
    1.49
    Activations Density 0.145%

    No Known Activations