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. 16030
    Prev
    Next
    INDEX
    Explanations

    references to qualities or characteristics that are common among groups of people

    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
    752
    +0.11
    0.3%
    732
    +0.11
    0.3%
    897
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    732
    +0.11
    0.05
    1276
    +0.11
    0.05
    406
    +0.10
    0.03
    Negative Logits
    timately
    -0.92
     unspeak
    -0.92
     nobly
    -0.91
     apprehen
    -0.90
     gaily
    -0.88
     disagre
    -0.88
     shewn
    -0.86
     vainly
    -0.82
     withal
    -0.82
     reconno
    -0.81
    POSITIVE LOGITS
    getIn
    0.54
     IN
    0.49
     lieu
    0.49
     terv
    0.48
     وتسجيلات
    0.47
    Jeden
    0.46
     situe
    0.46
     DANS
    0.46
     in
    0.45
     itin
    0.45
    Activations Density 0.274%

    No Known Activations