© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6650
    Prev
    Next
    INDEX
    Explanations

    phrases related to inclusivity, signaling, and messages of togetherness in a community

    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
    +0.18
    0.5%
    1967
    +0.09
    0.3%
    1987
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1543
    +0.18
    0.04
    248
    +0.09
    0.04
    1058
    +0.09
    0.04
    Negative Logits
     reluct
    -2.01
     maneu
    -1.96
     shenan
    -1.95
     fortn
    -1.80
     inappro
    -1.79
     impra
    -1.77
     strick
    -1.76
     increa
    -1.75
     apprehen
    -1.75
     disagre
    -1.75
    POSITIVE LOGITS
    jgl
    0.67
    الإنجليزية
    0.66
     worth
    0.65
    tonode
    0.64
    ValueStyle
    0.63
    ganu
    0.62
     noten
    0.61
    <bos>
    0.61
    wpi
    0.60
     Vikipedi
    0.59
    Activations Density 0.341%

    No Known Activations