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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 359
    Prev
    Next
    INDEX
    Explanations

    phrases related to boasting or bragging

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1363
    +0.12
    0.4%
    1490
    +0.10
    0.3%
    1464
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1490
    +0.12
    0.04
    1363
    +0.10
    0.02
    1056
    +0.10
    0.03
    Negative Logits
     nomine
    -0.85
     emphat
    -0.85
     carc
    -0.80
     embra
    -0.80
     suspic
    -0.80
     anse
    -0.80
     pessi
    -0.80
     musli
    -0.79
     casio
    -0.79
    🕗
    -0.78
    POSITIVE LOGITS
     boast
    0.98
     boasting
    0.95
     bragging
    0.86
     boasted
    0.86
     boasts
    0.86
     brag
    0.77
     proudly
    0.65
     about
    0.59
     glory
    0.58
     proud
    0.57
    Activations Density 0.129%

    No Known Activations