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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10500
    Prev
    Next
    INDEX
    Explanations

    mentions of the Academy Awards, also known as the Oscars

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Oscar awards and related terms

    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
    ohyd
    -0.75
     Anon
    -0.75
    ths
    -0.72
     mt
    -0.67
    ghan
    -0.67
    ciating
    -0.67
    ears
    -0.66
    imaru
    -0.63
    avez
    -0.62
     Uz
    -0.61
    POSITIVE LOGITS
     Awards
    1.24
     nominations
    1.21
     nominees
    1.12
     Award
    1.08
     winner
    1.07
     awards
    1.04
     nomination
    1.03
     nominee
    1.02
     nominated
    0.99
     winners
    0.97
    Activations Density 0.055%

    No Known Activations