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. 15065
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "gold" or related terms

    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
    596
    +0.16
    0.6%
    390
    +0.14
    0.6%
    1622
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1622
    +0.16
    0.03
    596
    +0.14
    0.03
    390
    +0.13
    0.03
    Negative Logits
     Baillargeon
    -0.53
    mlung
    -0.52
    verwijspagina
    -0.50
    InjectAttribute
    -0.49
     Nationen
    -0.49
    queryInterface
    -0.47
    PostExecute
    -0.47
    fjspx
    -0.47
    quelize
    -0.47
    PrototypeOf
    -0.47
    POSITIVE LOGITS
     GOLD
    1.26
     gold
    1.26
     Gold
    1.22
    gold
    1.21
    Gold
    1.18
    GOLD
    1.07
     Goldie
    0.88
     Goldsmith
    0.86
     doré
    0.85
     Goldstein
    0.85
    Activations Density 0.068%

    No Known Activations