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. 8291
    Prev
    Next
    INDEX
    Explanations

    information flow in the context of software systems, particularly comparing APIs to waiters in a restaurant analogy

    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
    2034
    +0.25
    0.8%
    1535
    +0.21
    0.7%
    1699
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.25
    0.09
    1535
    +0.21
    0.07
    610
    +0.17
    0.06
    Negative Logits
    Cześć
    -0.75
     šķ
    -0.74
    Hermoso
    -0.73
     Darum
    -0.71
     vairāk
    -0.71
    Conclusão
    -0.70
    Wię
    -0.69
     todav
    -0.69
     Apesar
    -0.68
     Zwar
    -0.68
    POSITIVE LOGITS
     Alternatively
    0.82
     Then
    0.78
     swarovski
    0.77
     Thereafter
    0.75
     Each
    0.73
     chré
    0.71
     écout
    0.71
     Afterwards
    0.71
     Once
    0.69
     malheureux
    0.68
    Activations Density 0.404%

    No Known Activations