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. 1614
    Prev
    Next
    INDEX
    Explanations

    keywords related to monetary policy and economic issues within the Eurozone

    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
    1937
    +0.18
    0.7%
    281
    +0.14
    0.5%
    1581
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.18
    0.03
    1065
    +0.14
    0.02
    421
    +0.14
    0.02
    Negative Logits
    yargs
    -0.65
    Anhalt
    -0.60
    PhysRevD
    -0.58
    bootstrapcdn
    -0.57
    DoubleQuotes
    -0.56
    ganu
    -0.55
     Ewig
    -0.55
    ModelMap
    -0.53
    tagHelperRunner
    -0.53
    NoSuchAlgorithm
    -0.52
    POSITIVE LOGITS
     increa
    1.23
    euro
    1.19
     euro
    1.18
    Euro
    1.18
     Euro
    1.17
     McLaugh
    1.16
     volunte
    1.10
     erad
    1.07
     suscep
    1.05
     jaya
    1.05
    Activations Density 0.071%

    No Known Activations