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. 1783
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or absence of actions or conditions

    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
    1.0%
    80
    +0.12
    0.5%
    1482
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.23
    0.06
    1590
    +0.12
    0.05
    32
    +0.12
    0.04
    Negative Logits
    <bos>
    -3.07
    while
    -0.65
     while
    -0.64
     we
    -0.59
    beforeAll
    -0.59
     protect
    -0.59
    fileprivate
    -0.58
    fputs
    -0.58
     extends
    -0.57
    //
    -0.56
    POSITIVE LOGITS
     ricardo
    1.31
     dises
    1.28
     santiago
    1.26
     stockholm
    1.25
     tucson
    1.24
     Minang
    1.24
     hcm
    1.23
     véhic
    1.22
     mef
    1.21
     napoli
    1.19
    Activations Density 0.164%

    No Known Activations