© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2373
    Prev
    Next
    INDEX
    Explanations

    expressions of fear for personal safety and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.31
    1.2%
    946
    +0.14
    0.5%
    658
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.31
    0.06
    509
    +0.14
    0.07
    2000
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.10
     intersper
    -0.78
     banish
    -0.76
     amass
    -0.72
     incarcer
    -0.72
     rehabilitate
    -0.70
     vanqu
    -0.70
     harmonize
    -0.69
     unify
    -0.69
     endow
    -0.67
    POSITIVE LOGITS
     safety
    0.86
    afety
    0.81
     Bekasi
    0.76
     Palembang
    0.73
     danger
    0.73
    safety
    0.73
     Tangerang
    0.73
     Makassar
    0.73
    cautionary
    0.71
    angering
    0.71
    Activations Density 0.853%

    No Known Activations