© 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. 4-RES-JB
    11. 22234
    Prev
    Next
    INDEX
    Explanations

    words related to the action of chewing or items to chew on

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of chewing and related terms

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

    No Comments

    Negative Logits
    inances
    -0.79
     Murder
    -0.71
     Abram
    -0.71
     priesthood
    -0.67
     Lowry
    -0.66
     kindred
    -0.64
     Centauri
    -0.64
    opoulos
    -0.63
    assian
    -0.62
    anni
    -0.59
    POSITIVE LOGITS
     chew
    0.99
     gum
    0.96
    enegger
    0.95
    esome
    0.85
    ername
    0.83
    paste
    0.82
     chewing
    0.81
    æĸ¹
    0.80
    ãģ¦
    0.80
    çİĭ
    0.79
    Activations Density 0.023%

    No Known Activations