© 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. 10-RES-JB
    11. 6650
    Prev
    Next
    INDEX
    Explanations

    YouTube and Google Drive links in text

    oai_token-act-pair · gpt-3.5-turbo

    web addresses, specifically links to YouTube and Google

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frie
    -0.80
    terday
    -0.71
     unused
    -0.67
     Letters
    -0.64
     Awakens
    -0.64
    -+-+
    -0.63
     Hebdo
    -0.60
     Diplom
    -0.60
     letters
    -0.59
     Bung
    -0.59
    POSITIVE LOGITS
    watch
    1.30
    embed
    0.98
    spread
    0.97
    channel
    0.95
    user
    0.89
    search
    0.88
    sites
    0.88
    share
    0.87
    gallery
    0.87
    youtu
    0.86
    Activations Density 0.012%

    No Known Activations