© 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. 10-RES-JB
    11. 13640
    Prev
    Next
    INDEX
    Explanations

    sentences expressing personal opinions or emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal emotions and reflections on experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ðŁĺ
    -0.84
    Kids
    -0.83
    Team
    -0.76
    kids
    -0.75
    goo
    -0.74
     messing
    -0.73
     freaking
    -0.73
     kinda
    -0.72
    Alert
    -0.72
     stunts
    -0.71
    POSITIVE LOGITS
     quotations
    1.20
     Chomsky
    1.13
     eluc
    1.11
     quotation
    1.06
     excerpt
    1.04
    ibliography
    1.03
     essay
    1.03
     summar
    1.02
     presupp
    1.01
     ital
    0.98
    Activations Density 0.452%

    No Known Activations