© 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. 3-RES-JB
    11. 4148
    Prev
    Next
    INDEX
    Explanations

    words related to cotton or materials made from cotton

    oai_token-act-pair · gpt-3.5-turbo

    references to cotton and its various uses or contexts

    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
    aphael
    -0.81
    irlf
    -0.71
    */(
    -0.71
    ctica
    -0.70
    CVE
    -0.69
    ebin
    -0.68
    arenthood
    -0.67
    cffffcc
    -0.65
    ONT
    -0.65
    onym
    -0.64
    POSITIVE LOGITS
     cotton
    1.10
    seed
    1.09
     wool
    1.04
     candy
    0.98
    bean
    0.95
     yarn
    0.95
    mouth
    0.91
    pee
    0.89
     gin
    0.88
    wood
    0.87
    Activations Density 0.010%

    No Known Activations