© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 681
    Prev
    Next
    INDEX
    Explanations

    situations where someone is upset or frustrated

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "upset" and related emotional expressions

    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
     livest
    -0.88
    glas
    -0.83
    artifacts
    -0.83
     liner
    -0.79
    ographies
    -0.77
    properties
    -0.76
    href
    -0.73
    istered
    -0.73
    vernment
    -0.72
    anamo
    -0.70
    POSITIVE LOGITS
     upset
    0.90
    dy
    0.89
    Brexit
    0.72
     uproar
    0.71
    wart
    0.68
     upsetting
    0.67
     Voldemort
    0.66
    @@@@
    0.63
    @@@@@@@@
    0.63
    TextColor
    0.63
    Activations Density 0.012%

    No Known Activations