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. 1179
    Prev
    Next
    INDEX
    Explanations

    the word "otherwise" across various contexts

    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
    +0.22
    1.2%
    545
    +0.11
    0.6%
    172
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.22
    0.02
    814
    +0.11
    0.02
    545
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.82
    RunWith
    -0.73
    ///**
    -0.73
    vector
    -0.71
    vec
    -0.71
    mu
    -0.71
    mun
    -0.70
    int
    -0.70
    addComponent
    -0.69
    flex
    -0.68
    POSITIVE LOGITS
     stockholm
    2.11
     toledo
    2.05
     volunte
    2.01
     chrysler
    1.97
     milano
    1.94
     tucson
    1.94
     maneu
    1.94
     eiffel
    1.92
     fortn
    1.90
     lamborghini
    1.90
    Activations Density 0.047%

    No Known Activations