© 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. 17124
    Prev
    Next
    INDEX
    Explanations

    questions or prompts for answers, often involving a specific task or information

    oai_token-act-pair · gpt-3.5-turbo

    words related to responding to questions or inquiries

    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
    chin
    -0.77
    heric
    -0.75
    zinski
    -0.73
     Vengeance
    -0.69
    akin
    -0.68
     Nanto
    -0.68
    robat
    -0.67
    gotten
    -0.66
    ufact
    -0.66
    nered
    -0.64
    POSITIVE LOGITS
    ysis
    1.00
    answer
    0.89
     questions
    0.88
     answ
    0.87
     Questions
    0.84
    swers
    0.83
     answering
    0.82
     yes
    0.80
    Answer
    0.77
    question
    0.77
    Activations Density 0.020%

    No Known Activations