© 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. 17368
    Prev
    Next
    INDEX
    Explanations

    mentions of shortcuts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of shortcuts or the concept of taking shortcuts

    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
    cano
    -0.90
    mos
    -0.86
    externalActionCode
    -0.81
    endi
    -0.78
    uana
    -0.75
    ystem
    -0.73
    conom
    -0.73
    Else
    -0.72
    yss
    -0.71
    bane
    -0.70
    POSITIVE LOGITS
    ãĥĥãĥĪ
    0.81
    itud
    0.75
     shortcuts
    0.71
     Lear
    0.70
    aneously
    0.70
    bledon
    0.69
    osen
    0.65
    comings
    0.64
    cair
    0.63
    voy
    0.63
    Activations Density 0.065%

    No Known Activations