© 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. 8-RES-JB
    11. 6558
    Prev
    Next
    INDEX
    Explanations

    awards and nominations for various categories like Best Actor, Best Picture, Best Song, and Best Animated Feature

    oai_token-act-pair · gpt-3.5-turbo

    mentions of awards and their categories in relation to film and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IGHTS
    -0.76
     inval
    -0.73
    gypt
    -0.70
    heter
    -0.65
    pher
    -0.64
     coli
    -0.63
     hopping
    -0.62
     traced
    -0.61
    vt
    -0.61
     probing
    -0.61
    POSITIVE LOGITS
    seller
    1.04
    iary
    1.03
     Selling
    0.97
     Practices
    0.93
    iaries
    0.92
     Seller
    0.85
     Overall
    0.84
     Worst
    0.84
    selling
    0.81
     Picture
    0.81
    Activations Density 0.049%

    No Known Activations