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. 8224
    Prev
    Next
    INDEX
    Explanations

    military-related terms and equipment

    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
    2019
    +0.38
    1.3%
    304
    +0.18
    0.6%
    381
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.38
    0.06
    359
    +0.18
    0.04
    946
    +0.17
    0.04
    Negative Logits
     to
    -0.84
     in
    -0.83
     be
    -0.82
     on
    -0.81
     actually
    -0.81
     as
    -0.80
     the
    -0.79
     a
    -0.79
     by
    -0.79
     of
    -0.78
    POSITIVE LOGITS
     ridu
    1.59
     mef
    1.59
     Kategor
    1.58
     embra
    1.56
     ordina
    1.55
     dispen
    1.50
     confé
    1.50
     alkoh
    1.49
     ivi
    1.48
     keramik
    1.46
    Activations Density 0.136%

    No Known Activations