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. 15875
    Prev
    Next
    INDEX
    Explanations

    descriptive words indicating abundance or variety

    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
    1252
    +0.11
    0.3%
    776
    +0.10
    0.3%
    382
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.11
    0.04
    1252
    +0.10
    0.05
    1
    +0.10
    0.05
    Negative Logits
     Sén
    -0.85
     Sympathi
    -0.75
     Bartholo
    -0.71
     vagu
    -0.71
     Châ
    -0.70
     McInt
    -0.70
     Theile
    -0.70
     Marín
    -0.69
     Manufact
    -0.69
     Áng
    -0.69
    POSITIVE LOGITS
     of
    0.65
    ("")]
    
    0.57
     assortment
    0.56
     range
    0.55
    ValueStyle
    0.55
     array
    0.54
     Vielzahl
    0.53
    Източници
    0.53
     variety
    0.53
    range
    0.50
    Activations Density 0.217%

    No Known Activations