© 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. 13269
    Prev
    Next
    INDEX
    Explanations

    adverbs related to drastic or dramatic change

    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
    478
    +0.14
    0.5%
    976
    +0.11
    0.4%
    1056
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1056
    +0.14
    0.05
    976
    +0.11
    0.04
    478
    +0.09
    0.04
    Negative Logits
     attemp
    -0.97
     intersper
    -0.97
     kön
    -0.96
     abstrait
    -0.89
     reluct
    -0.87
     eki
    -0.87
     inev
    -0.86
     encomp
    -0.85
     praktik
    -0.85
     délib
    -0.84
    POSITIVE LOGITS
    ificantly
    0.76
    haustible
    0.68
    pertise
    0.67
    IALLY
    0.64
    medies
    0.63
     greatly
    0.62
     marginBottom
    0.62
    ecuted
    0.62
     autunno
    0.59
    requently
    0.59
    Activations Density 0.130%

    No Known Activations