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. 1506
    Prev
    Next
    INDEX
    Explanations

    specific numerical information, including counts and measurements

    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
    382
    +0.15
    0.4%
    1456
    +0.08
    0.2%
    381
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.15
    0.05
    1456
    +0.08
    0.03
    736
    +0.08
    0.04
    Negative Logits
     solidar
    -0.84
    település
    -0.81
     noten
    -0.77
     smtplib
    -0.76
    Geplaatst
    -0.75
    Tembelea
    -0.72
     Logement
    -0.70
     pymysql
    -0.70
     spion
    -0.69
     vernac
    -0.69
    POSITIVE LOGITS
     intersper
    1.01
     two
    0.93
     four
    0.89
     three
    0.88
     unspeak
    0.88
     five
    0.87
     apprehen
    0.86
     ineffec
    0.85
     impra
    0.84
     six
    0.84
    Activations Density 0.280%

    No Known Activations