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. 13528
    Prev
    Next
    INDEX
    Explanations

    exclamatory statements and onomatopoeic expressions

    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
    240
    +0.11
    0.3%
    1691
    +0.10
    0.3%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.11
    0.03
    240
    +0.10
    0.02
    577
    +0.10
    0.02
    Negative Logits
    Kenmerken
    -0.65
    Indien
    -0.57
     Boven
    -0.51
    mide
    -0.49
    Flere
    -0.49
     Hva
    -0.48
     roda
    -0.47
     Verder
    -0.47
    المصادر
    -0.47
     Mú
    -0.47
    POSITIVE LOGITS
     unden
    1.16
     excru
    1.15
     accla
    1.14
     fatis
    1.12
     scrat
    1.10
     lidl
    1.07
     effe
    1.06
     volunte
    1.06
     perfet
    1.05
     unve
    1.05
    Activations Density 0.071%

    No Known Activations