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. 322
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or formulas

    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
    674
    +0.16
    0.5%
    876
    +0.11
    0.4%
    1980
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.16
    0.00
    51
    +0.11
    0.01
    1317
    +0.09
    0.02
    Negative Logits
     horrend
    -0.86
     shenan
    -0.86
     maverick
    -0.84
     nurt
    -0.83
     pitbull
    -0.79
     pathfinder
    -0.77
     rancho
    -0.76
     sophistic
    -0.75
     diabo
    -0.75
     mercurial
    -0.74
    POSITIVE LOGITS
     territo
    1.41
     maksi
    1.38
     meis
    1.34
     naer
    1.27
     chèvre
    1.25
     dises
    1.23
     poire
    1.22
     levis
    1.22
     haer
    1.22
     frambo
    1.21
    Activations Density 0.042%

    No Known Activations