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. 0-RES-JB
    6. 17428
    Prev
    Next
    INDEX
    Explanations

    the word "Instead"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "instead" and phrases that suggest alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Can
    -0.64
     Orig
    -0.63
     Se
    -0.63
     Frequ
    -0.61
     Hazard
    -0.61
     Tong
    -0.60
     Log
    -0.59
     Swe
    -0.59
     Family
    -0.59
     Fall
    -0.59
    POSITIVE LOGITS
    Instead
    3.01
    Rather
    2.26
    instead
    1.72
    Nonetheless
    1.53
    Nevertheless
    1.49
    Fortunately
    1.45
    Luckily
    1.44
    Therefore
    1.39
    Moreover
    1.39
    Thankfully
    1.38
    Activations Density 0.044%

    No Known Activations