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. 1185
    Prev
    Next
    INDEX
    Explanations

    terms related to reactions and responses to events or situations

    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
    +0.23
    1.3%
    896
    +0.15
    0.8%
    370
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.23
    0.03
    370
    +0.15
    0.03
    1981
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.97
    declare
    -0.63
    <?
    -0.63
    /***
    
    -0.61
    host
    -0.58
    /*++
    -0.56
     host
    -0.56
    didSet
    -0.56
    notifyListeners
    -0.56
    unif
    -0.55
    POSITIVE LOGITS
     bandung
    1.49
     jawa
    1.46
     stockholm
    1.42
     bangkok
    1.42
     jaya
    1.40
     hcm
    1.40
     vne
    1.36
     lidl
    1.32
     wien
    1.31
     riviera
    1.31
    Activations Density 0.051%

    No Known Activations