© 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. 8-RES-JB
    11. 6495
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion and physical descriptions of facial expressions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of subtle emotional nuances, particularly those indicating sarcasm or smirking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ©Ł
    -0.82
    DragonMagazine
    -0.77
     opio
    -0.77
    Sources
    -0.75
     GOODMAN
    -0.74
    soDeliveryDate
    -0.73
    UTC
    -0.72
    arthed
    -0.71
    Reviewer
    -0.70
    geons
    -0.68
    POSITIVE LOGITS
     grin
    1.10
     smile
    1.06
     expression
    1.04
     demeanor
    1.04
     expressions
    1.01
     laughter
    0.98
     emot
    0.92
     amused
    0.89
     smiles
    0.89
     incred
    0.89
    Activations Density 0.223%

    No Known Activations