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. 553
    Prev
    Next
    INDEX
    Explanations

    references to sizes, numbers, and changes in quantities

    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
    1177
    +0.09
    0.3%
    1499
    +0.08
    0.2%
    1839
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1839
    +0.09
    0.04
    1499
    +0.08
    0.04
    1383
    +0.08
    0.03
    Negative Logits
     meis
    -1.02
     haer
    -0.97
     Sén
    -0.97
     Mâ
    -0.96
     Palest
    -0.96
     intersper
    -0.95
     ché
    -0.95
     châ
    -0.94
     mef
    -0.94
     accla
    -0.94
    POSITIVE LOGITS
     involved
    0.85
     used
    0.78
     required
    0.77
     needed
    0.75
     taken
    0.73
     available
    0.70
     consumed
    0.69
     spent
    0.69
     offered
    0.69
     employed
    0.69
    Activations Density 0.312%

    No Known Activations