© 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. 2231
    Prev
    Next
    INDEX
    Explanations

    mentions of political and diplomatic activities in Yemen

    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
    1842
    +0.18
    0.5%
    1120
    +0.11
    0.3%
    394
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1290
    +0.18
    0.07
    939
    +0.11
    0.06
    81
    +0.10
    0.03
    Negative Logits
     disreg
    -1.54
     shenan
    -1.51
     encomp
    -1.47
     milf
    -1.46
     reluct
    -1.46
     intersper
    -1.44
     impra
    -1.43
     hentai
    -1.42
     downvotes
    -1.42
     emphat
    -1.41
    POSITIVE LOGITS
     ostavi
    0.66
    ISupport
    0.66
     peaceful
    0.64
     peacefully
    0.61
     peace
    0.61
    queryInterface
    0.60
    TableField
    0.56
    новниш
    0.56
    frain
    0.56
    Brainz
    0.56
    Activations Density 0.495%

    No Known Activations