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. 2944
    Prev
    Next
    INDEX
    Explanations

    countries, political organizations, and geographic locations

    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
    50
    +0.41
    1.5%
    1577
    +0.14
    0.5%
    1959
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.41
    0.17
    227
    +0.14
    0.19
    1177
    +0.08
    0.09
    Negative Logits
    ⓧ
    -0.83
     trattano
    -0.76
    település
    -0.75
    💼
    -0.73
     revisor
    -0.72
    
    
    -0.72
     citazioni
    -0.70
     getNombre
    -0.68
     emot
    -0.66
     abstracta
    -0.66
    POSITIVE LOGITS
     Bartholo
    1.06
     McLaugh
    1.05
     sophistic
    1.02
     impra
    1.00
     Thier
    0.97
     unspeak
    0.96
     Theile
    0.95
     Gorb
    0.95
     Rine
    0.94
     maneu
    0.94
    Activations Density 3.218%

    No Known Activations