Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 4248
    Prev
    Next
    INDEX
    Explanations

    the word "okay" being used in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    affirmations of acceptability or reassurance

    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
    enegger
    -0.72
    Ly
    -0.71
    marine
    -0.71
    hunt
    -0.70
    rament
    -0.69
    cycl
    -0.68
    rylic
    -0.68
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.67
    Ult
    -0.66
    ortex
    -0.65
    POSITIVE LOGITS
     okay
    1.21
     ok
    1.11
     OK
    1.01
     alright
    1.01
     Okay
    0.92
    terday
    0.86
     bye
    0.86
     Alright
    0.85
    lahoma
    0.85
    Okay
    0.76
    Activations Density 0.005%

    No Known Activations