© 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. 0-RES-JB
    11. 13302
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, specifically issues related to knees and pain

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific names or unique identifiers related to items or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sched
    -0.66
     Juven
    -0.63
     predictions
    -0.61
     competitiveness
    -0.61
     Dynamics
    -0.60
     Growth
    -0.59
     Lep
    -0.59
     Strategy
    -0.58
     MEN
    -0.58
     Cell
    -0.58
    POSITIVE LOGITS
    nee
    4.37
    enne
    2.03
    nel
    1.19
    lynn
    1.16
     une
    1.10
    sie
    1.09
    onna
    0.99
    naire
    0.97
    arma
    0.97
    kee
    0.96
    Activations Density 0.027%

    No Known Activations