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. 15426
    Prev
    Next
    INDEX
    Explanations

    references to the English language

    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
    1491
    +0.13
    0.5%
    1325
    +0.12
    0.5%
    545
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1376
    +0.13
    0.03
    1491
    +0.12
    0.03
    545
    +0.11
    0.03
    Negative Logits
    ffilm
    -0.61
    ആ
    -0.56
    Sklici
    -0.54
    icône
    -0.52
     referenties
    -0.52
    ಇ
    -0.51
    Història
    -0.51
    glTex
    -0.49
    Palmar
    -0.49
    Бахар
    -0.49
    POSITIVE LOGITS
     Áng
    1.32
     English
    1.13
     England
    1.08
     english
    1.01
    England
    1.00
    English
    0.98
     ENGLISH
    0.98
     isabel
    0.97
     Engl
    0.96
     ricardo
    0.95
    Activations Density 0.076%

    No Known Activations