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. 19479
    Prev
    Next
    INDEX
    Explanations

    questions within text

    oai_token-act-pair · gpt-3.5-turbo

    interrogative punctuation and phrases that indicate questioning 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
    hed
    -0.73
     guiActiveUnfocused
    -0.72
    ozyg
    -0.70
     utter
    -0.69
     innocence
    -0.68
     unlucky
    -0.66
    lled
    -0.64
    oÄŁ
    -0.64
     unus
    -0.64
    ascus
    -0.63
    POSITIVE LOGITS
     Fortunately
    1.23
     Specifically
    1.21
     Luckily
    1.17
     Ideally
    1.15
     Thankfully
    1.13
     Especially
    1.12
     Here
    1.09
     Instead
    1.06
     Unfortunately
    1.05
     Below
    1.03
    Activations Density 0.415%

    No Known Activations