© 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. 2-RES-JB
    11. 1025
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to facial features

    oai_token-act-pair · gpt-3.5-turbo

    references to facial features and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hedon
    -0.79
    ensable
    -0.74
    debian
    -0.71
    awaru
    -0.69
    uden
    -0.68
    æ©Ł
    -0.68
     Pharma
    -0.67
    aday
    -0.64
    claimer
    -0.64
    ileged
    -0.64
    POSITIVE LOGITS
     facial
    1.08
     expressions
    1.01
     hair
    0.97
     beard
    0.93
     portraits
    0.90
     tattoos
    0.88
     recognition
    0.87
     Hair
    0.87
     hairst
    0.84
     makeup
    0.84
    Activations Density 0.013%

    No Known Activations