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. 13629
    Prev
    Next
    INDEX
    Explanations

    phrases related to praising or criticizing specific actions or behaviors

    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
    1177
    +0.11
    0.3%
    453
    +0.11
    0.3%
    1499
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.11
    0.05
    1056
    +0.11
    0.05
    100
    +0.09
    0.04
    Negative Logits
     tricot
    -0.79
     suscep
    -0.75
     vespa
    -0.74
     cushi
    -0.72
     cabrio
    -0.70
     thermomix
    -0.69
     bordeaux
    -0.68
     teflon
    -0.65
     tdci
    -0.62
     lpg
    -0.61
    POSITIVE LOGITS
    Manbalar
    0.86
     Minang
    0.82
     Banjar
    0.81
     Palembang
    0.81
     Karang
    0.79
     Lampung
    0.78
     Banten
    0.69
     Jambi
    0.68
     Pekan
    0.68
     Muhamma
    0.68
    Activations Density 0.283%

    No Known Activations