© 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. 14865
    Prev
    Next
    INDEX
    Explanations

    instances of the word "switch" being used in a technical context

    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
    689
    +0.15
    0.5%
    1407
    +0.12
    0.4%
    36
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    689
    +0.15
    0.03
    1407
    +0.12
    0.02
    1142
    +0.10
    0.02
    Negative Logits
     minimalis
    -0.64
     solidar
    -0.59
     kosme
    -0.57
     praktik
    -0.57
     alkoh
    -0.57
     hek
    -0.56
    Ảnh
    -0.55
     kriminal
    -0.55
     roh
    -0.54
     ideolog
    -0.53
    POSITIVE LOGITS
     switch
    1.20
     switches
    1.18
     Switch
    1.13
     switched
    1.12
    switches
    1.10
     Switching
    1.08
     Switches
    1.08
     switching
    1.07
    Switch
    1.04
     SWITCH
    1.03
    Activations Density 0.063%

    No Known Activations