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. 20714
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "well" followed by a number rating

    oai_token-act-pair · gpt-3.5-turbo

    the adverb "well."

    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
    ategory
    -0.62
    TAG
    -0.59
     generated
    -0.58
     torn
    -0.58
    Ts
    -0.58
     glam
    -0.58
     finance
    -0.57
     style
    -0.57
     pric
    -0.57
     generation
    -0.56
    POSITIVE LOGITS
    well
    4.61
    Well
    1.48
     well
    1.32
     Well
    1.27
    hey
    1.19
    way
    1.17
    wait
    1.11
    we
    1.06
    worth
    1.02
    stable
    1.01
    Activations Density 0.010%

    No Known Activations