© 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. 8-RES-JB
    11. 6522
    Prev
    Next
    INDEX
    Explanations

    phrases containing special characters and terms that have a mix of letters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    symbols that represent emotional expressions or sentiments

    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
    anwhile
    -0.73
    creen
    -0.69
    EStream
    -0.68
     scatter
    -0.66
    ortium
    -0.63
     Tradable
    -0.61
     Incarn
    -0.60
     shack
    -0.60
     misunder
    -0.59
     guiName
    -0.59
    POSITIVE LOGITS
    ¬
    1.11
    ¡
    1.09
    Ĵ
    1.09
    ľ
    1.06
    ¦
    1.04
    į
    1.02
    ĸ
    1.02
    ĵ
    1.01
    ı
    0.98
    ķ
    0.97
    Activations Density 0.145%

    No Known Activations