© 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. 4-RES-JB
    11. 3730
    Prev
    Next
    INDEX
    Explanations

    phrases related to making fun of or mocking something or someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve making fun of people, situations, or concepts

    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
     laun
    -0.73
    assetsadobe
    -0.71
    bryce
    -0.68
    earchers
    -0.67
    xual
    -0.65
    quickShipAvailable
    -0.61
     horizont
    -0.60
     tiss
    -0.60
     Introduced
    -0.59
     constitu
    -0.59
    POSITIVE LOGITS
    sense
    0.65
     happen
    0.65
     recess
    0.65
    ãĥĥãĤ¯
    0.63
     noises
    0.62
    roads
    0.60
    ificant
    0.60
     splash
    0.60
     Ys
    0.59
    olphins
    0.58
    Activations Density 0.216%

    No Known Activations