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. 10109
    Prev
    Next
    INDEX
    Explanations

    references to military tactics or operations

    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
    +0.24
    0.9%
    1577
    +0.20
    0.7%
    2019
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.24
    0.25
    1959
    +0.20
    0.25
    16
    +0.12
    0.22
    Negative Logits
     kilomet
    -0.87
    TagMode
    -0.87
    RectangleBorder
    -0.86
     minuter
    -0.82
     beginnetje
    -0.81
     cucharadas
    -0.80
     revisor
    -0.80
     geografic
    -0.80
     Wikimédia
    -0.80
    ביוגרפיה
    -0.79
    POSITIVE LOGITS
     shenan
    2.36
     impra
    2.35
     reluct
    2.33
     disagre
    2.25
     encomp
    2.22
     unspeak
    2.20
     sophistic
    2.16
     maneu
    2.14
     accla
    2.13
     uninten
    2.13
    Activations Density 9.085%

    No Known Activations