© 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. 2310
    Prev
    Next
    INDEX
    Explanations

    terms related to computer processors and technology

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology performance and customer solutions

    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
    toggle
    -0.75
    iatus
    -0.75
     externalToEVAOnly
    -0.75
     todd
    -0.73
     whining
    -0.72
    shit
    -0.72
     grop
    -0.71
     plun
    -0.71
     disclaimer
    -0.71
    edit
    -0.70
    POSITIVE LOGITS
     innovative
    1.15
     interoper
    1.12
     seamless
    1.09
     innovate
    1.07
     innovation
    1.05
     innovations
    1.04
     unparalleled
    1.04
     unmatched
    1.02
     scalable
    0.97
     transformative
    0.97
    Activations Density 0.586%

    No Known Activations