© 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. 9536
    Prev
    Next
    INDEX
    Explanations

    laundry-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to laundry and related tasks

    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
    */(
    -0.85
    alez
    -0.82
    olar
    -0.79
    itol
    -0.72
    umar
    -0.72
    ulhu
    -0.72
    pps
    -0.72
    ologies
    -0.72
    oid
    -0.72
    ioch
    -0.71
    POSITIVE LOGITS
     laundry
    1.18
    ©¶æ¥µ
    0.87
     laund
    0.78
    robe
    0.76
     soap
    0.75
     basket
    0.73
     closet
    0.71
     undert
    0.71
    stairs
    0.70
    æ©Ł
    0.69
    Activations Density 0.005%

    No Known Activations