© 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. 6882
    Prev
    Next
    INDEX
    Explanations

    words related to chemical substances, particularly "glycerine" and "viscerally."

    oai_token-act-pair · gpt-3.5-turbo

    words related to bodily fluids and their derived products

    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
     Kund
    -0.71
     Skydragon
    -0.65
     reins
    -0.63
     leash
    -0.58
     Lak
    -0.56
     diverse
    -0.56
    sight
    -0.55
     valuable
    -0.55
     hunger
    -0.55
     solitary
    -0.55
    POSITIVE LOGITS
    cer
    1.31
    berus
    1.15
    pter
    0.98
    oute
    0.95
    rane
    0.92
    ipher
    0.91
    ozo
    0.89
    culus
    0.88
    chio
    0.86
    ruits
    0.86
    Activations Density 0.007%

    No Known Activations