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. 6-RES-JB
    6. 19501
    Prev
    Next
    INDEX
    Explanations

    instances of the word "otherwise"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "otherwise," indicating a contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.68
     fullback
    -0.68
     horizont
    -0.65
    nesday
    -0.64
     scrimmage
    -0.63
     Camel
    -0.62
     Coffee
    -0.60
    ocracy
    -0.59
     Sta
    -0.59
     Lyndon
    -0.58
    POSITIVE LOGITS
    worldly
    0.88
    heastern
    0.78
     behaved
    0.73
    FFFF
    0.72
    amas
    0.72
    arily
    0.70
    ghazi
    0.70
    erella
    0.68
    models
    0.67
     inclined
    0.66
    Activations Density 0.010%

    No Known Activations