© 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. 10-RES-JB
    11. 11176
    Prev
    Next
    INDEX
    Explanations

    phrases that end with a witty or clever one-liner

    oai_token-act-pair · gpt-3.5-turbo

    humorous elements or comedic expressions in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MFT
    -0.79
    ranch
    -0.79
     Horizons
    -0.74
    osponsors
    -0.71
    agate
    -0.70
     GOODMAN
    -0.67
     Branch
    -0.64
     Located
    -0.63
     biodiversity
    -0.63
     Sovere
    -0.63
    POSITIVE LOGITS
     uttered
    1.20
     aloud
    1.20
     inco
    1.15
     sarcast
    1.14
     unint
    1.10
     gib
    1.07
     ("
    1.07
     apologizing
    1.03
     politely
    0.97
     implying
    0.96
    Activations Density 0.478%

    No Known Activations