Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8185
    Prev
    Next
    INDEX
    Explanations

    contractions with an apostrophe

    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
    50
    +0.16
    0.5%
    1967
    +0.16
    0.5%
    1253
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.16
    0.13
    478
    +0.16
    0.11
    1533
    +0.13
    0.07
    Negative Logits
     actionTypes
    -0.68
     firebaseConfig
    -0.66
    nasel
    -0.64
    wieś
    -0.62
     classNames
    -0.59
    polski
    -0.58
    Fakta
    -0.58
     Vainqueur
    -0.56
     userEmail
    -0.55
    Ofer
    -0.55
    POSITIVE LOGITS
     effe
    0.93
     inder
    0.89
     fers
    0.86
     wein
    0.85
     slan
    0.85
     levis
    0.85
     wien
    0.84
     waer
    0.84
     ciga
    0.83
     torba
    0.82
    Activations Density 1.080%

    No Known Activations