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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 819
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal beliefs and interpersonal interactions

    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
    +0.10
    0.3%
    1919
    +0.10
    0.3%
    453
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.07
    2025
    +0.10
    0.06
    658
    +0.08
    0.06
    Negative Logits
     cabrio
    -1.02
     bordeaux
    -1.00
     wien
    -0.99
     embra
    -0.95
     Realt
    -0.95
     mef
    -0.95
     vespa
    -0.95
     coq
    -0.94
     fta
    -0.93
     stockholm
    -0.93
    POSITIVE LOGITS
    GEBURTSDATUM
    0.68
     personally
    0.67
     “
    0.63
     himself
    0.62
     «
    0.61
     "
    0.60
    StructEnd
    0.60
    elemField
    0.59
     “[
    0.56
    Vaata
    0.56
    Activations Density 0.552%

    No Known Activations