© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22526
    Prev
    Next
    INDEX
    Explanations

    mentions of specific flight incidents and related terms, such as flight numbers and relevant entities

    oai_token-act-pair · gpt-3.5-turbo

    references to missing flights and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Republic
    -0.88
    ãĤ½
    -0.83
    ãĤ¦
    -0.83
    swick
    -0.79
     Republic
    -0.77
    ãĥ¼ãĥĨ
    -0.75
    Square
    -0.74
    ptroller
    -0.74
    cer
    -0.72
    ãĤ±
    -0.71
    POSITIVE LOGITS
     Lumpur
    1.31
     MH
    0.98
    370
    0.96
    MH
    0.90
    oney
    0.86
    rals
    0.80
    adish
    0.79
    awei
    0.78
    allery
    0.77
    Ħ¢
    0.73
    Activations Density 0.010%

    No Known Activations