© 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. 4-RES-JB
    11. 22521
    Prev
    Next
    INDEX
    Explanations

    situations or individuals that are experiencing frustration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "frustrated" and related feelings of frustration

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

    No Comments

    Negative Logits
    icrobial
    -0.96
    orthy
    -0.88
    fman
    -0.77
    etics
    -0.75
    oak
    -0.73
    enko
    -0.72
    ahead
    -0.71
    enses
    -0.70
    amation
    -0.70
    izations
    -0.70
    POSITIVE LOGITS
     frustration
    0.96
     frustrations
    0.86
     frustrated
    0.83
     frust
    0.79
     exasper
    0.77
     frustrating
    0.67
     annoyance
    0.65
     unbearable
    0.65
     unhappy
    0.65
    DEM
    0.65
    Activations Density 0.021%

    No Known Activations