© 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. 8-RES-JB
    11. 6421
    Prev
    Next
    INDEX
    Explanations

    sentences ending in either a period or a question mark

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and the structure of sentences

    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
    uers
    -0.87
     innov
    -0.77
     rall
    -0.75
     proport
    -0.74
    eatured
    -0.74
    eatures
    -0.72
     notor
    -0.71
     critically
    -0.71
     inund
    -0.71
     predominantly
    -0.71
    POSITIVE LOGITS
     Anyway
    1.42
     Especially
    1.28
     Sorry
    1.25
     Alright
    1.25
     Besides
    1.23
     Hmm
    1.19
     Yeah
    1.19
     You
    1.17
     Maybe
    1.17
     Didn
    1.14
    Activations Density 0.297%

    No Known Activations