© 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. 10-RES-JB
    11. 8510
    Prev
    Next
    INDEX
    Explanations

    references to images, videos, and footage

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or details in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledge
    -0.85
    gem
    -0.82
    advertising
    -0.82
    amazon
    -0.82
    Tier
    -0.77
    abel
    -0.76
    rss
    -0.74
    ESPN
    -0.72
    netflix
    -0.71
    achus
    -0.70
    POSITIVE LOGITS
     aftermath
    1.33
     workings
    1.14
     devastation
    1.08
     scene
    1.07
     impending
    1.03
     underside
    1.02
     unfolding
    0.99
     proceedings
    0.97
     entire
    0.97
     entirety
    0.96
    Activations Density 0.289%

    No Known Activations