© 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. 6-RES-JB
    11. 17117
    Prev
    Next
    INDEX
    Explanations

    references to legal matters and government actions

    oai_token-act-pair · gpt-3.5-turbo

    empty or blank sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cial
    -0.76
    ftime
    -0.71
    aunder
    -0.69
    aba
    -0.68
    ceive
    -0.67
    strate
    -0.66
    udo
    -0.65
    âĢIJ
    -0.64
    ample
    -0.63
    ilater
    -0.63
    POSITIVE LOGITS
     easiest
    1.06
     safest
    1.03
     hardest
    1.01
     slightest
    1.00
     biggest
    0.99
     latter
    0.99
     strongest
    0.98
     simplest
    0.98
     entire
    0.96
     heaviest
    0.95
    Activations Density 0.234%

    No Known Activations