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. 11936
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical sensations or emotional states

    oai_token-act-pair · gpt-3.5-turbo

    elements that engage and involve the audience or viewer

    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
     patents
    -0.74
     Quit
    -0.73
     lawsuits
    -0.69
    fork
    -0.68
     Median
    -0.65
     bitch
    -0.64
     trump
    -0.64
     Stall
    -0.63
     stocks
    -0.62
     quotas
    -0.62
    POSITIVE LOGITS
     glimpse
    1.10
     glimps
    1.05
     gaze
    1.00
     irresist
    0.91
     discover
    0.91
    agine
    0.89
     voy
    0.87
     explore
    0.87
    iscover
    0.87
     marvel
    0.87
    Activations Density 0.519%

    No Known Activations