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. 1312
    Prev
    Next
    INDEX
    Explanations

    steps or actions related to software development and testing

    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
    872
    +0.13
    0.4%
    876
    +0.09
    0.3%
    1150
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1134
    +0.13
    0.07
    1843
    +0.09
    0.06
    1377
    +0.09
    0.04
    Negative Logits
     Horizonte
    -0.69
     sartén
    -0.59
    ulipas
    -0.58
     Unito
    -0.57
     Bajos
    -0.57
    Zeneca
    -0.56
     terrorismo
    -0.55
     Baillargeon
    -0.54
    demment
    -0.54
     WQS
    -0.53
    POSITIVE LOGITS
     impra
    1.02
     maneu
    0.96
     encomp
    0.96
     intersper
    0.95
     disreg
    0.93
     uninten
    0.91
     shenan
    0.88
     unlaw
    0.86
     resear
    0.86
     reluct
    0.85
    Activations Density 2.064%

    No Known Activations