© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 702
    Prev
    Next
    INDEX
    Explanations

    instances of the word "answers"

    oai_token-act-pair · gpt-4-turbo

    answers to questions presented in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms related to questions and answers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ony
    -0.65
    ufact
    -0.63
    yss
    -0.62
    ucket
    -0.62
    arde
    -0.61
    rie
    -0.61
    ouf
    -0.61
    yards
    -0.61
     Sabha
    -0.59
     Vengeance
    -0.59
    POSITIVE LOGITS
     answ
    1.13
    swers
    1.10
    answer
    0.95
    ysis
    0.94
     answered
    0.93
     answers
    0.91
     answer
    0.89
    Answer
    0.89
     thereto
    0.87
    chool
    0.81
    Activations Density 0.012%

    No Known Activations