© 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. 3-RES-JB
    11. 10068
    Prev
    Next
    INDEX
    Explanations

    descriptions related to observing or depicting emotions through eye expressions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "eyes" as a symbol of emotion or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adium
    -0.73
    ggies
    -0.67
    artifacts
    -0.63
     Whats
    -0.63
    channelAvailability
    -0.62
    vich
    -0.61
    interstitial
    -0.60
     Violent
    -0.59
     IGF
    -0.58
    TON
    -0.57
    POSITIVE LOGITS
    ight
    1.11
     sockets
    0.96
    pots
    0.89
    creen
    0.87
    pring
    0.86
    abre
    0.86
    bridge
    0.83
    erver
    0.82
    bre
    0.81
    ports
    0.80
    Activations Density 0.012%

    No Known Activations