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. 619
    Prev
    Next
    INDEX
    Explanations

    instances of organization names or entities mentioned together

    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
    198
    +0.19
    0.6%
    50
    +0.12
    0.4%
    738
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.19
    0.05
    939
    +0.12
    0.06
    198
    +0.11
    0.06
    Negative Logits
     économies
    -0.84
     églises
    -0.84
     négociations
    -0.81
     vœux
    -0.77
     étages
    -0.77
     kasarigan
    -0.76
     bénéfices
    -0.76
     navires
    -0.76
     dégâts
    -0.74
     créations
    -0.73
    POSITIVE LOGITS
     fta
    1.12
     fte
    1.09
     erad
    1.03
     oun
    1.02
     increa
    1.02
     aen
    0.99
    ceff
    0.98
     secon
    0.98
    fordable
    0.97
     reluct
    0.97
    Activations Density 0.330%

    No Known Activations