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. 15637
    Prev
    Next
    INDEX
    Explanations

    plays in a sports game

    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
    1535
    +0.20
    0.6%
    2019
    +0.18
    0.6%
    2034
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.20
    0.10
    1535
    +0.18
    0.08
    22
    +0.17
    0.07
    Negative Logits
     pama
    -0.91
     labi
    -0.87
     churrasco
    -0.81
     pousada
    -0.81
     teras
    -0.77
     esat
    -0.77
     affitto
    -0.77
     beira
    -0.75
     azule
    -0.74
     unwarran
    -0.74
    POSITIVE LOGITS
     Then
    0.73
     Afterwards
    0.70
    Then
    0.62
     Thereafter
    0.61
     Afterward
    0.61
     Subsequently
    0.60
     This
    0.59
     Later
    0.59
    Afterwards
    0.57
     Finally
    0.57
    Activations Density 0.550%

    No Known Activations