© 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 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. 6264
    Prev
    Next
    INDEX
    Explanations

    phrases relating to critically evaluating or appreciating aspects of a product

    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
    +0.09
    0.2%
    70
    +0.08
    0.2%
    275
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1155
    +0.09
    0.03
    836
    +0.08
    0.02
    275
    +0.08
    0.02
    Negative Logits
    Dzięki
    -0.66
    Może
    -0.64
    Przyp
    -0.63
    Skład
    -0.62
    Kiedy
    -0.61
    Prí
    -0.61
    Зміст
    -0.61
    Pozri
    -0.60
    listdir
    -0.60
    Dlaczego
    -0.60
    POSITIVE LOGITS
     laun
    1.04
     uniqu
    1.03
     fars
    1.00
     immen
    1.00
     daf
    0.99
     tyn
    0.99
     effe
    0.97
     elek
    0.97
     daz
    0.96
     ordina
    0.95
    Activations Density 0.259%

    No Known Activations