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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 3868
    Prev
    Next
    INDEX
    Explanations

    variants of the word "switch"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "switch" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    za
    -0.71
    Chicken
    -0.68
    amina
    -0.66
    vez
    -0.65
    ifice
    -0.63
    USD
    -0.63
     Nutrition
    -0.63
    nutrition
    -0.62
     VIDEOS
    -0.61
    vae
    -0.59
    POSITIVE LOGITS
     switch
    1.05
     switches
    1.01
    switch
    0.92
    blade
    0.89
    aroo
    0.88
    inson
    0.87
    backs
    0.85
    grass
    0.81
     switching
    0.81
     switched
    0.81
    Activations Density 0.014%

    No Known Activations