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. 11-RES-JB
    6. 3970
    Prev
    Next
    INDEX
    Explanations

    potentially Clickbait phrases with ellipses and prompts to read more

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or pauses in text, indicating an incomplete thought or continuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adas
    -0.69
    oche
    -0.68
    æĪ¦
    -0.66
    hiba
    -0.66
    èĢ
    -0.60
    flo
    -0.60
     spar
    -0.60
    Ĭ±
    -0.60
    .):
    -0.60
    acket
    -0.59
    POSITIVE LOGITS
     Continue
    1.08
     Appears
    0.97
     Read
    0.92
     Retrieved
    0.84
     READ
    0.83
     Written
    0.81
     read
    0.78
     Learn
    0.76
     Free
    0.76
    <|endoftext|>
    0.76
    Activations Density 0.066%

    No Known Activations