© 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. 8-RES-JB
    11. 17660
    Prev
    Next
    INDEX
    Explanations

    phrases that involve a call to action or a directive

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marketable
    -0.65
     horizont
    -0.64
     quadru
    -0.64
     rall
    -0.64
     landfill
    -0.62
     renewables
    -0.61
     seiz
    -0.60
     stranded
    -0.60
     ceremon
    -0.57
     stret
    -0.57
    POSITIVE LOGITS
    âĢ
    1.33
    »
    1.26
    "(
    1.24
    ¨
    1.18
    âĸł
    1.13
    ``
    1.11
    ^^
    1.10
    âĸº
    1.09
    Â
    1.09
    ^
    1.08
    Activations Density 0.500%

    No Known Activations