© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 20798
    Prev
    Next
    INDEX
    Explanations

    words related to savoring food or experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of salvation or savory experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     filings
    -0.73
    ptin
    -0.70
     defective
    -0.69
     misplaced
    -0.67
    HOME
    -0.67
    hibition
    -0.67
    quartered
    -0.65
    backer
    -0.65
     tightening
    -0.65
    Reloaded
    -0.65
    POSITIVE LOGITS
    iour
    1.25
    annah
    1.08
    iors
    1.02
     sav
    1.01
    itives
    0.97
    illas
    0.92
    iew
    0.89
    ants
    0.88
    icer
    0.87
    ouring
    0.87
    Activations Density 0.009%

    No Known Activations