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. 8332
    Prev
    Next
    INDEX
    Explanations

    time-related entities such as days, weeks, months, and hours

    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
    776
    +0.10
    0.3%
    490
    +0.09
    0.3%
    1013
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1384
    +0.10
    0.05
    1025
    +0.09
    0.04
    490
    +0.09
    0.03
    Negative Logits
    Gep
    -0.57
     &___
    -0.54
    featureID
    -0.53
    Beit
    -0.53
    cydow
    -0.51
     Gnaden
    -0.51
    gatsby
    -0.51
    LookAnd
    -0.51
    webElementXpaths
    -0.50
    TabStop
    -0.50
    POSITIVE LOGITS
     unwarran
    0.85
     pamph
    0.82
     ingrat
    0.78
     disagre
    0.78
     Shakspeare
    0.74
     McLaugh
    0.70
     Mónica
    0.69
     despotism
    0.68
    alnız
    0.66
     courtier
    0.65
    Activations Density 0.122%

    No Known Activations