Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10597
    Prev
    Next
    INDEX
    Explanations

    words related to the action of switching

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "switch" and its variations related to changing or transitioning between options or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etermined
    -0.76
    vere
    -0.70
    adata
    -0.68
    cision
    -0.66
    ictionary
    -0.62
    bis
    -0.62
    conom
    -0.61
    alion
    -0.61
    brance
    -0.61
    nutrition
    -0.61
    POSITIVE LOGITS
     gears
    1.15
     sides
    1.10
     allegiance
    1.06
     between
    1.00
     alleg
    1.00
     genders
    0.98
     continents
    0.96
     stances
    0.96
     lanes
    0.93
     seamlessly
    0.90
    Activations Density 0.067%

    No Known Activations