© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 12227
    Prev
    Next
    INDEX
    Explanations

    the word "exception" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words related to exceptions and perceptions

    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
     shar
    -0.81
     encl
    -0.71
     gra
    -0.69
     scrap
    -0.67
     rebuild
    -0.67
     resc
    -0.66
     reconc
    -0.63
     recol
    -0.63
     shrink
    -0.63
     smoot
    -0.61
    POSITIVE LOGITS
    ception
    4.52
    ceptions
    2.89
    ceptive
    2.15
    ceive
    1.95
    CEPT
    1.89
    ceived
    1.71
    cept
    1.69
    ceptor
    1.49
    ference
    1.22
    ceivable
    1.12
    Activations Density 0.015%

    No Known Activations