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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5984
    Prev
    Next
    INDEX
    Explanations

    references to conflict and military engagement

    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
    298
    +0.15
    0.5%
    1145
    +0.11
    0.4%
    58
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.15
    0.03
    58
    +0.11
    0.02
    270
    +0.10
    0.02
    Negative Logits
    zoom
    -0.46
    transitions
    -0.44
    ConstraintMaker
    -0.43
    StrictEqual
    -0.42
    las
    -0.41
    formik
    -0.41
    Abstra
    -0.40
    bir
    -0.40
    DataURL
    -0.39
    sol
    -0.39
    POSITIVE LOGITS
     enemy
    1.04
     Enemy
    0.93
     enemies
    0.93
    enemy
    0.86
     cabrio
    0.86
     maksi
    0.86
     Enemies
    0.83
    Enemy
    0.79
     hilux
    0.79
     Bekasi
    0.78
    Activations Density 0.078%

    No Known Activations