© 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. 19766
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical pain

    oai_token-act-pair · gpt-3.5-turbo

    references to pain

    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
    eor
    -0.84
    eton
    -0.84
    riminal
    -0.82
    indal
    -0.79
    yss
    -0.79
    sonian
    -0.75
    VERTISEMENT
    -0.73
    ordan
    -0.72
    orthy
    -0.71
    Ü
    -0.68
    POSITIVE LOGITS
    killers
    1.28
     pain
    1.23
    staking
    1.19
    killer
    1.03
     agony
    0.99
    terness
    0.95
     Pain
    0.94
    pain
    0.93
     reliever
    0.91
    lessly
    0.91
    Activations Density 0.015%

    No Known Activations