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. 8392
    Prev
    Next
    INDEX
    Explanations

    information related to software and applications

    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
    +0.15
    0.5%
    382
    +0.14
    0.4%
    2034
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.15
    0.07
    1265
    +0.14
    0.06
    736
    +0.13
    0.07
    Negative Logits
     mef
    -1.65
     maroc
    -1.55
     ordina
    -1.55
     milano
    -1.54
     nutr
    -1.54
     pixabay
    -1.50
     obé
    -1.50
     alkoh
    -1.49
     monaster
    -1.49
     fei
    -1.47
    POSITIVE LOGITS
     then
    0.94
     and
    0.87
     which
    0.81
     but
    0.80
    then
    0.75
     그리고
    0.74
     followed
    0.73
     rồi
    0.72
    RTLR
    0.71
     however
    0.70
    Activations Density 0.333%

    No Known Activations