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. 1678
    Prev
    Next
    INDEX
    Explanations

    information related to news articles and press releases

    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
    674
    +0.12
    0.4%
    1870
    +0.11
    0.3%
    1967
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.12
    0.04
    417
    +0.11
    0.03
    1473
    +0.10
    0.01
    Negative Logits
     GeoNames
    -0.79
    Hvad
    -0.73
    Preço
    -0.71
    calciatore
    -0.70
    hdessä
    -0.69
    Flere
    -0.69
     ***!
    -0.68
    GRANTED
    -0.67
    Eacute
    -0.67
    Dienstag
    -0.66
    POSITIVE LOGITS
     encomp
    1.41
     accla
    1.34
     depic
    1.33
     intersper
    1.33
     shenan
    1.28
     maneu
    1.27
     volunte
    1.24
     reluct
    1.22
     practition
    1.21
     indestru
    1.21
    Activations Density 0.145%

    No Known Activations