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. 14357
    Prev
    Next
    INDEX
    Explanations

    words related to occurrences or events

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of events

    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
    ãĥ¥
    -0.64
    cho
    -0.62
     tailor
    -0.61
     tweak
    -0.60
     smarter
    -0.58
     modelling
    -0.58
     Hack
    -0.57
     dub
    -0.55
     Get
    -0.54
     Dak
    -0.54
    POSITIVE LOGITS
     occurred
    3.44
     happened
    2.34
     occurs
    2.33
     transpired
    2.25
     occur
    2.09
     ensued
    1.88
     occurring
    1.75
     resulted
    1.72
     coincided
    1.69
     arose
    1.65
    Activations Density 0.013%

    No Known Activations