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. 15390
    Prev
    Next
    INDEX
    Explanations

    phrases related to various forms of art and art-related activities

    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
    486
    +0.14
    0.6%
    1296
    +0.14
    0.5%
    1974
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    486
    +0.14
    0.03
    25
    +0.14
    0.04
    1296
    +0.13
    0.03
    Negative Logits
     تضيفلها
    -0.58
    cloudflare
    -0.46
    Igles
    -0.46
     pageable
    -0.45
    силання
    -0.44
    remadura
    -0.43
    তথ্যসূত্র
    -0.43
    oldown
    -0.43
     hiperten
    -0.43
     ideje
    -0.42
    POSITIVE LOGITS
     art
    1.29
     Art
    1.22
    Art
    1.18
     ART
    1.15
     arts
    1.02
    art
    1.01
     Arts
    0.87
     artwork
    0.87
    ART
    0.87
     artworks
    0.85
    Activations Density 0.071%

    No Known Activations