© 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. 11-RES-JB
    11. 981
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer processors and technology companies

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases related to corporate leadership and technology product announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     negro
    -0.85
     Lovecraft
    -0.81
     sinners
    -0.79
    ocaust
    -0.79
     lol
    -0.77
     starvation
    -0.75
     crappy
    -0.74
     Confederate
    -0.73
     ruined
    -0.72
     mockery
    -0.72
    POSITIVE LOGITS
     roadmap
    1.21
     Partner
    1.20
     IoT
    1.09
    /
    1.07
     leveraging
    1.06
     Acceler
    1.03
     Platform
    1.02
     SDK
    1.01
     accelerate
    1.01
     Azure
    1.00
    Activations Density 0.691%

    No Known Activations