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. 8217
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative debates

    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
    1499
    +0.10
    0.3%
    1899
    +0.09
    0.3%
    872
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1864
    +0.10
    0.04
    1860
    +0.09
    0.04
    143
    +0.09
    0.05
    Negative Logits
     tupperware
    -1.03
     fluo
    -1.00
     ibiza
    -0.96
     bordeaux
    -0.95
     oleo
    -0.94
     trouva
    -0.94
     thermomix
    -0.94
     cannes
    -0.92
     swarovski
    -0.90
     Intere
    -0.89
    POSITIVE LOGITS
     argue
    0.97
    argument
    0.84
     argues
    0.84
     argued
    0.80
    Arguments
    0.78
    arguments
    0.77
     argument
    0.76
     arguments
    0.74
     arguing
    0.73
     argumentos
    0.71
    Activations Density 0.445%

    No Known Activations