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. 3-RES-JB
    6. 21828
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings or punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     footing
    -0.80
     volunt
    -0.74
     conservatism
    -0.73
     involuntary
    -0.72
    uly
    -0.72
    ibur
    -0.72
    ling
    -0.72
    oshenko
    -0.71
    untarily
    -0.70
     manif
    -0.70
    POSITIVE LOGITS
     Unfortunately
    1.23
     Thankfully
    1.20
     Hopefully
    1.20
     Especially
    1.19
     However
    1.19
     Additionally
    1.17
     Whilst
    1.16
     Luckily
    1.14
     Regardless
    1.13
     Alternatively
    1.12
    Activations Density 1.435%

    No Known Activations