© 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. 7-RES-JB
    11. 23460
    Prev
    Next
    INDEX
    Explanations

    words related to annoyance or displeasure

    oai_token-act-pair · gpt-3.5-turbo

    expressions of annoyance and unpleasantness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arnaev
    -0.88
    yss
    -0.84
    bard
    -0.83
    ework
    -0.82
    ardless
    -0.82
    ariat
    -0.82
    udeau
    -0.82
    ynthesis
    -0.82
    acebook
    -0.81
    cellence
    -0.81
    POSITIVE LOGITS
     nuisance
    1.10
     headaches
    0.93
     annoy
    0.92
     pests
    0.90
     annoyance
    0.87
     inconven
    0.85
     glare
    0.83
     obnoxious
    0.82
     spikes
    0.79
     headache
    0.79
    Activations Density 0.083%

    No Known Activations