© 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. 18650
    Prev
    Next
    INDEX
    Explanations

    words related to comedy and humor

    oai_token-act-pair · gpt-3.5-turbo

    colloquial terms or slang related to informal social interactions or groups

    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
    ibaba
    -0.75
    angan
    -0.72
     results
    -0.65
    utterstock
    -0.63
    zb
    -0.62
     invasive
    -0.62
     expiration
    -0.61
    ı
    -0.60
     annexation
    -0.60
    andise
    -0.59
    POSITIVE LOGITS
     who
    1.07
    esses
    1.06
     whom
    0.94
     extraord
    0.90
    Joined
    0.88
    who
    0.84
    friend
    0.83
    ãĥĦ
    0.81
    doms
    0.81
    ess
    0.81
    Activations Density 0.403%

    No Known Activations