© 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 EvalsExportsinterp-engineNEWAPI 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. 5121
    Prev
    Next
    INDEX
    Explanations

    instances of the word "panic" or related words and contexts

    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
    1742
    +0.13
    0.4%
    1363
    +0.13
    0.4%
    1233
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.13
    0.03
    1363
    +0.13
    0.03
    1742
    +0.12
    0.02
    Negative Logits
     migli
    -0.62
     maroc
    -0.60
     ciment
    -0.59
     roma
    -0.57
     canne
    -0.56
     taba
    -0.56
     eus
    -0.54
     hina
    -0.54
     biograf
    -0.54
    unicip
    -0.54
    POSITIVE LOGITS
     panic
    1.14
     Panic
    1.01
     panicked
    0.96
    panic
    0.93
    Panic
    0.89
     alarm
    0.65
     shewn
    0.64
     alarmed
    0.60
     heapq
    0.60
     anxiety
    0.59
    Activations Density 0.111%

    No Known Activations