© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3844
    Prev
    Next
    INDEX
    Explanations

    words related to shields and defensive actions

    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
    1339
    +0.13
    0.5%
    241
    +0.13
    0.5%
    805
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1425
    +0.13
    0.02
    241
    +0.13
    0.02
    890
    +0.13
    0.02
    Negative Logits
     reconno
    -0.65
     renou
    -0.65
     hairc
    -0.64
     gaily
    -0.64
     fameux
    -0.63
    mistak
    -0.63
     vété
    -0.61
     intersper
    -0.61
     apprehen
    -0.59
     shenan
    -0.59
    POSITIVE LOGITS
     shield
    1.47
     Shield
    1.32
    shield
    1.29
     shields
    1.29
    Shield
    1.16
     Shields
    1.14
    shields
    1.06
     shielding
    1.05
     SHIELD
    1.01
    hield
    0.94
    Activations Density 0.097%

    No Known Activations