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. 6-RES-JB
    6. 23399
    Prev
    Next
    INDEX
    Explanations

    phrases containing the interjection "Oh," often used to express surprise or draw attention

    oai_token-act-pair · gpt-3.5-turbo

    frequent conversational interjections or filler phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.93
    İĭ
    -0.82
    BILITIES
    -0.81
    ngth
    -0.80
    camp
    -0.75
    wcs
    -0.75
    MpServer
    -0.75
    UGC
    -0.69
    arov
    -0.68
    robe
    -0.67
    POSITIVE LOGITS
     dear
    0.92
     yes
    0.92
     yeah
    0.91
     Mistress
    0.73
     hello
    0.73
     Wait
    0.71
     shame
    0.66
     hurry
    0.66
     Miss
    0.65
     wow
    0.65
    Activations Density 0.038%

    No Known Activations