© 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. 7038
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pepper" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to pepper spray

    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
    ADRA
    -0.83
    hematic
    -0.75
    ģĸ
    -0.71
    ĸļ
    -0.71
    UE
    -0.69
     Objective
    -0.67
    urai
    -0.66
     Cannot
    -0.63
    ür
    -0.63
    Ĵ
    -0.62
    POSITIVE LOGITS
    mint
    1.58
     flakes
    0.95
     spray
    0.91
    cone
    0.89
    vine
    0.88
     sprayed
    0.87
    oni
    0.87
    onis
    0.86
     pepper
    0.84
    cake
    0.83
    Activations Density 0.035%

    No Known Activations