© 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. 1-RES-JB
    11. 20147
    Prev
    Next
    INDEX
    Explanations

    sentences that start with "Okay" and sometimes "Huh."

    oai_token-act-pair · gpt-3.5-turbo

    repetitive affirmations or agreement expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cycl
    -0.74
     brim
    -0.68
    lled
    -0.67
    advert
    -0.66
    articles
    -0.63
     vain
    -0.63
    ifle
    -0.63
     sexes
    -0.62
    effic
    -0.61
    ache
    -0.61
    POSITIVE LOGITS
    Okay
    1.23
     Okay
    1.16
     Alright
    1.14
    Alright
    1.11
    lahoma
    1.03
     okay
    0.96
     OK
    0.95
    OK
    0.92
     alright
    0.90
     bye
    0.90
    Activations Density 0.010%

    No Known Activations