© 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. 9-RES-JB
    11. 10059
    Prev
    Next
    INDEX
    Explanations

    references to software or products, particularly related to spying or surveillance

    oai_token-act-pair · gpt-3.5-turbo

    elements related to marketing and competitive advantages

    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
     Ramsay
    -0.86
     Slate
    -0.86
     BuzzFeed
    -0.84
     Whedon
    -0.81
     Bolton
    -0.80
    "—
    -0.79
     Burke
    -0.78
     Bray
    -0.78
     Parsons
    -0.78
    Advertisement
    -0.77
    POSITIVE LOGITS
     resear
    1.08
    ´
    1.07
     happ
    1.05
     till
    1.03
     english
    0.97
    pecially
    0.93
     evid
    0.88
     android
    0.88
     !!
    0.87
     alot
    0.87
    Activations Density 3.400%

    No Known Activations