© 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. 8-RES-JB
    11. 21769
    Prev
    Next
    INDEX
    Explanations

    URLs starting with "www"

    oai_token-act-pair · gpt-3.5-turbo

    web URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Courage
    -0.65
     Ballard
    -0.61
    rained
    -0.59
     proportion
    -0.59
    RO
    -0.59
     sadd
    -0.58
     BART
    -0.58
     expulsion
    -0.58
    oted
    -0.57
     Rend
    -0.56
    POSITIVE LOGITS
    www
    0.99
    natureconservancy
    0.93
    youtube
    0.87
    xual
    0.84
    forums
    0.84
    ibaba
    0.84
    ctl
    0.83
    ertodd
    0.79
    :/
    0.78
    ebin
    0.77
    Activations Density 0.007%

    No Known Activations