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. 1092
    Prev
    Next
    INDEX
    Explanations

    instances of the word "embrace" and its variations

    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
    +0.25
    1.3%
    25
    +0.12
    0.6%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.25
    0.02
    1604
    +0.12
    0.02
    1413
    +0.11
    0.02
    Negative Logits
    <bos>
    -3.05
    HasIndex
    -0.82
    SizeMode
    -0.78
    CodeDom
    -0.76
    OneToMany
    -0.76
    public
    -0.73
    ComponentModel
    -0.72
    ManyToMany
    -0.71
    /**
    
    -0.70
    WriteHeader
    -0.70
    POSITIVE LOGITS
     stockholm
    2.14
     strick
    2.09
     impra
    2.07
     increa
    2.04
     fta
    2.03
     embra
    2.03
     madonna
    2.00
     affor
    2.00
     maneu
    1.97
     snoopy
    1.97
    Activations Density 0.044%

    No Known Activations