Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17927
    Prev
    Next
    INDEX
    Explanations

    questions within text

    oai_token-act-pair · gpt-3.5-turbo

    the word "What" indicating questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shore
    -0.65
    heter
    -0.63
    ulic
    -0.62
    fish
    -0.61
    println
    -0.59
    Lago
    -0.58
    lich
    -0.58
    ped
    -0.57
    POR
    -0.57
    atory
    -0.57
    POSITIVE LOGITS
    soever
    1.39
     happens
    1.16
     happened
    1.04
     happ
    1.00
     distinguishes
    0.91
     transpired
    0.89
     exactly
    0.88
     kinds
    0.87
     constitutes
    0.86
     else
    0.86
    Activations Density 0.082%

    No Known Activations