© 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. 6250
    Prev
    Next
    INDEX
    Explanations

    words related to positive emotions or satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    instances of satisfaction or positive emotions

    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
    ut
    -0.77
    onut
    -0.74
    uli
    -0.73
    perse
    -0.73
    ciplinary
    -0.71
    çīĪ
    -0.71
    ammy
    -0.69
    ums
    -0.65
    ipers
    -0.65
    gger
    -0.64
    POSITIVE LOGITS
     pleased
    0.71
     surprises
    0.68
     satisfied
    0.67
     Wynne
    0.66
     happily
    0.66
    iated
    0.66
     enough
    0.65
     congr
    0.63
     seeing
    0.62
     gladly
    0.62
    Activations Density 0.060%

    No Known Activations