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. 10-RES-JB
    6. 22097
    Prev
    Next
    INDEX
    Explanations

    periods at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain periods or end statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compet
    -0.78
    yip
    -0.76
     issuer
    -0.75
     aven
    -0.74
    esty
    -0.73
     undecided
    -0.72
     advis
    -0.72
     defe
    -0.71
     interven
    -0.70
     quickest
    -0.70
    POSITIVE LOGITS
     Today
    1.59
     Eventually
    1.59
     Now
    1.47
     Later
    1.43
     Then
    1.41
     Slowly
    1.36
     Suddenly
    1.34
     Initially
    1.33
     Consequently
    1.33
     Since
    1.31
    Activations Density 0.380%

    No Known Activations