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. 9-RES-JB
    6. 20348
    Prev
    Next
    INDEX
    Explanations

    phrases related to missed opportunities or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    the word "have" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aris
    -0.62
    iling
    -0.61
    osi
    -0.58
    ature
    -0.56
     muse
    -0.55
    iddle
    -0.55
     trolling
    -0.54
     forestry
    -0.53
     Recap
    -0.51
    anwhile
    -0.51
    POSITIVE LOGITS
    been
    1.20
     been
    1.20
     gotten
    1.10
     liked
    1.00
     gone
    0.97
     benefited
    0.96
     Been
    0.90
    had
    0.89
     prevented
    0.88
     fared
    0.84
    Activations Density 0.060%

    No Known Activations