© 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. 16153
    Prev
    Next
    INDEX
    Explanations

    phrases containing the structure "do-it-yourself" or "DIY"

    oai_token-act-pair · gpt-3.5-turbo

    negative expressions or concepts

    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
     buoy
    -0.78
     ranks
    -0.77
     Tier
    -0.75
     cutting
    -0.75
     hus
    -0.75
     gauge
    -0.75
     entry
    -0.73
     capped
    -0.73
     casting
    -0.73
     moder
    -0.72
    POSITIVE LOGITS
    your
    1.53
    whatever
    1.47
    enough
    1.46
    everything
    1.43
    shit
    1.42
    anything
    1.41
    every
    1.39
    same
    1.39
    you
    1.38
    matter
    1.37
    Activations Density 0.077%

    No Known Activations