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. 13991
    Prev
    Next
    INDEX
    Explanations

    **verbs related to discovery or formation**

    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
    549
    +0.10
    0.3%
    1413
    +0.10
    0.3%
    1110
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1413
    +0.10
    0.03
    549
    +0.10
    0.04
    559
    +0.09
    0.04
    Negative Logits
     depic
    -1.93
     reluct
    -1.89
     increa
    -1.88
     encomp
    -1.84
     impra
    -1.81
     shenan
    -1.80
     maneu
    -1.77
     unve
    -1.75
     indestru
    -1.75
     inev
    -1.73
    POSITIVE LOGITS
    find
    1.01
     find
    1.00
     finds
    0.88
     found
    0.87
     Find
    0.84
    FIND
    0.84
    Find
    0.82
    found
    0.80
     finding
    0.79
    finder
    0.77
    Activations Density 0.221%

    No Known Activations