© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12342
    Prev
    Next
    INDEX
    Explanations

    job-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    It activates on plural nouns that label groups, categories, or types of entities.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    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
    +0.12
    0.3%
    1823
    +0.08
    0.2%
    1919
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    908
    +0.12
    0.04
    2006
    +0.08
    0.06
    1652
    +0.08
    0.05
    Negative Logits
     lorenzo
    -0.91
     alberto
    -0.91
     sergio
    -0.90
     fernando
    -0.90
     loren
    -0.89
     roberto
    -0.87
     napoli
    -0.87
     javier
    -0.85
     milano
    -0.83
     mef
    -0.83
    POSITIVE LOGITS
     whose
    0.79
     belonging
    0.65
     who
    0.63
     containing
    0.60
    日至
    0.59
     deemed
    0.58
    whose
    0.57
     تضيفلها
    0.56
     that
    0.55
     Zwar
    0.55
    Activations Density 0.383%

    No Known Activations