Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 1294
    Prev
    Next
    INDEX
    Explanations

    a blend of different genres or elements in creative works

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe a combination of humor and serious themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imester
    -0.90
     "$:/
    -0.80
    arger
    -0.77
    Sphere
    -0.77
    prus
    -0.76
    ":"/
    -0.76
    umerable
    -0.75
    owe
    -0.75
    ģĸ
    -0.74
    acent
    -0.74
    POSITIVE LOGITS
     quirky
    1.20
     humor
    1.19
     laughs
    1.19
     witty
    1.18
     playful
    1.18
     gritty
    1.15
     banter
    1.14
     nostalgia
    1.14
     intrigue
    1.13
     cheesy
    1.12
    Activations Density 0.570%

    No Known Activations