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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10563
    Prev
    Next
    INDEX
    Explanations

    phrases related to weather and nature changes

    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
    2015
    +0.15
    0.5%
    184
    +0.15
    0.5%
    1446
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1380
    +0.15
    0.03
    1446
    +0.15
    0.04
    509
    +0.13
    0.06
    Negative Logits
     ***!
    -0.80
    ಠ
    -0.79
    Autoritní
    -0.76
    Carreira
    -0.74
    Erreferentziak
    -0.72
    Filmo
    -0.70
    Geografi
    -0.69
    Lähteet
    -0.68
    ⇑
    -0.67
    fjspx
    -0.65
    POSITIVE LOGITS
     michelin
    1.80
     snoopy
    1.78
     disreg
    1.73
     milf
    1.72
     lidl
    1.70
     scrat
    1.69
     hairc
    1.68
     affor
    1.66
     tiffany
    1.64
     swarovski
    1.63
    Activations Density 0.347%

    No Known Activations