© 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. 4170
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-reflection and awareness

    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
    1741
    +0.10
    0.3%
    1385
    +0.10
    0.3%
    488
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.10
    0.06
    488
    +0.10
    0.05
    1967
    +0.07
    0.04
    Negative Logits
     reluct
    -1.66
     shenan
    -1.63
     disagre
    -1.63
     excru
    -1.60
     unve
    -1.59
     maneu
    -1.59
     impra
    -1.59
     strick
    -1.57
     fuf
    -1.57
     increa
    -1.56
    POSITIVE LOGITS
     same
    0.68
     amount
    0.64
     kinds
    0.64
     things
    0.63
     type
    0.61
     ganas
    0.61
     những
    0.61
     kind
    0.61
     minuta
    0.60
     way
    0.59
    Activations Density 0.351%

    No Known Activations