© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 14546
    Prev
    Next
    INDEX
    Explanations

    URLs or hyperlinks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of hyperlinks or references to URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bered
    -0.78
    ricular
    -0.72
     dough
    -0.68
     heav
    -0.67
     crust
    -0.65
     Peb
    -0.64
     comfort
    -0.64
     chicks
    -0.63
     saf
    -0.63
     caliber
    -0.63
    POSITIVE LOGITS
    link
    1.40
    Link
    1.10
    edin
    0.85
    lash
    0.82
    eton
    0.81
    tenance
    0.80
    Pierre
    0.79
    lihood
    0.78
    Mas
    0.78
    ibrary
    0.77
    Activations Density 0.011%

    No Known Activations