© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4662
    Prev
    Next
    INDEX
    Explanations

    terms related to military actions or conflicts

    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
    1177
    +0.14
    0.4%
    690
    +0.13
    0.4%
    752
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    569
    +0.14
    0.07
    509
    +0.13
    0.07
    1531
    +0.09
    0.05
    Negative Logits
    of
    -0.56
    for
    -0.56
    3
    -0.55
    1
    -0.54
    Để
    -0.53
    Pass
    -0.53
    CO
    -0.53
    ‎
    -0.53
    Fax
    -0.52
    Co
    -0.52
    POSITIVE LOGITS
     Souha
    1.56
     Traité
    1.46
     Autre
    1.44
     Docteur
    1.37
     Église
    1.36
     Jérusalem
    1.33
     regardant
    1.31
     Juf
    1.31
     hairc
    1.30
     Messieurs
    1.30
    Activations Density 0.497%

    No Known Activations