© 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. 1-RES-JB
    11. 11257
    Prev
    Next
    INDEX
    Explanations

    words related to irritation or irritants

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "irritate" and its variations related to discomfort or annoyance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oros
    -0.77
    edom
    -0.75
    iolet
    -0.71
    Mand
    -0.69
     Frozen
    -0.67
    emin
    -0.66
     Ragnarok
    -0.65
     Moonlight
    -0.64
    redit
    -0.64
    elta
    -0.63
    POSITIVE LOGITS
     irrit
    1.37
    inkle
    1.09
     irritation
    1.07
     irritated
    0.96
     Flavoring
    0.91
     Dull
    0.86
     irritating
    0.82
    utical
    0.81
     acid
    0.80
     sore
    0.78
    Activations Density 0.021%

    No Known Activations