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. 8221
    Prev
    Next
    INDEX
    Explanations

    references to legal or bureaucratic documents

    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
    1741
    +0.30
    1.1%
    50
    +0.17
    0.6%
    1535
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1045
    +0.30
    0.05
    397
    +0.17
    0.04
    241
    +0.13
    0.05
    Negative Logits
     shenan
    -0.81
     withal
    -0.74
     disreg
    -0.73
     maneu
    -0.71
     friable
    -0.71
     intersper
    -0.70
     subgoals
    -0.69
     apprehen
    -0.68
     diffusi
    -0.67
     gaily
    -0.67
    POSITIVE LOGITS
    Katso
    0.79
     prouve
    0.78
    Glej
    0.74
     préc
    0.74
    Mitä
    0.73
     légiti
    0.67
     gouver
    0.67
     Thé
    0.66
     prétend
    0.65
     Guzmán
    0.62
    Activations Density 0.216%

    No Known Activations