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. 8777
    Prev
    Next
    INDEX
    Explanations

    mentions or indications of something existing or having existed

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "existed" in various contexts

    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
    os
    -0.56
    ft
    -0.56
     Rounds
    -0.56
     drops
    -0.54
     knockout
    -0.54
     Charity
    -0.52
    ts
    -0.51
     2018
    -0.51
     Laser
    -0.51
     Pack
    -0.51
    POSITIVE LOGITS
     existed
    3.60
     resided
    1.66
     flourished
    1.55
     lasted
    1.54
     exist
    1.54
     belonged
    1.51
     mattered
    1.48
     prevailed
    1.46
     exists
    1.43
     arose
    1.39
    Activations Density 0.009%

    No Known Activations