© 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. 1-RES-JB
    11. 6545
    Prev
    Next
    INDEX
    Explanations

    questions or prompts followed by the idea of being answered or resolved

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "answered" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovie
    -0.81
    ouf
    -0.72
    cakes
    -0.70
    owitz
    -0.68
    zinski
    -0.66
    bat
    -0.66
    rug
    -0.66
    ierre
    -0.65
    enic
    -0.65
    lim
    -0.65
    POSITIVE LOGITS
     answered
    1.20
     answ
    1.19
    swers
    1.18
     answering
    1.10
     answer
    1.06
    answer
    1.03
     answers
    1.00
    Answer
    0.97
     Answers
    0.95
     Answer
    0.95
    Activations Density 0.009%

    No Known Activations