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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 19528
    Prev
    Next
    INDEX
    Explanations

    statements or comments within a text

    oai_token-act-pair · gpt-3.5-turbo

    various forms of punctuation or sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mosqu
    -0.79
     gobl
    -0.75
     aven
    -0.69
     remission
    -0.69
     ceremonial
    -0.68
     slightest
    -0.68
     eternity
    -0.68
     surname
    -0.68
     utter
    -0.68
     enjoyment
    -0.68
    POSITIVE LOGITS
     REUTERS
    1.06
     Moreover
    1.05
     Specifically
    1.00
     Increasing
    1.00
     Especially
    1.00
     Recent
    0.97
     Additionally
    0.97
     Experts
    0.96
     But
    0.95
     Indeed
    0.95
    Activations Density 0.527%

    No Known Activations