© 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. 6-RES-JB
    11. 22656
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with the words "Can you"

    oai_token-act-pair · gpt-3.5-turbo

    questions and requests for assistance involving the word "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylum
    -0.72
    hyde
    -0.67
     Flags
    -0.64
    teen
    -0.63
    history
    -0.62
    Lenin
    -0.61
    mails
    -0.60
    assic
    -0.60
    artifacts
    -0.58
     Respons
    -0.58
    POSITIVE LOGITS
     afford
    0.96
     tell
    0.87
     accommodate
    0.87
     reconcile
    0.84
     safely
    0.83
     convince
    0.81
     conceive
    0.81
     be
    0.81
     compare
    0.80
     quantify
    0.79
    Activations Density 0.040%

    No Known Activations