© 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. 7-RES-JB
    11. 12680
    Prev
    Next
    INDEX
    Explanations

    various forms and contexts of the word "fun."

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to enjoyment and humor

    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
    priority
    -0.82
    isSpecialOrderable
    -0.81
    ledged
    -0.79
    awei
    -0.77
     dilig
    -0.76
     priority
    -0.76
     mandate
    -0.76
     mortgages
    -0.75
     holdings
    -0.75
    insured
    -0.75
    POSITIVE LOGITS
     jokes
    1.27
     trivia
    1.03
     joke
    0.96
     joking
    0.94
     banter
    0.93
     Animation
    0.93
     Doodle
    0.92
     GIF
    0.91
     Pixar
    0.91
     gigg
    0.90
    Activations Density 0.350%

    No Known Activations