© 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. 14716
    Prev
    Next
    INDEX
    Explanations

    phrases related to food establishments and menus

    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
    1013
    +0.17
    0.5%
    1703
    +0.12
    0.4%
    736
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.17
    0.06
    64
    +0.12
    0.03
    1013
    +0.10
    0.05
    Negative Logits
     churrasco
    -0.81
     smtplib
    -0.81
     pimiento
    -0.75
     autunno
    -0.73
     possesso
    -0.73
     virtù
    -0.72
     pican
    -0.72
     pylab
    -0.69
     Erlangen
    -0.68
     skimage
    -0.68
    POSITIVE LOGITS
     cushi
    1.01
     unve
    0.96
     friable
    0.94
     shenan
    0.89
     affor
    0.86
     hairc
    0.85
     scrat
    0.82
     snoopy
    0.81
     reluct
    0.81
     unspeak
    0.81
    Activations Density 0.326%

    No Known Activations