© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4419
    Prev
    Next
    INDEX
    Explanations

    links or URLs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    periods, signifying the end of sentences or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millenn
    -1.10
     challeng
    -1.09
     exha
    -1.07
     reluct
    -1.04
     mosqu
    -0.95
    ò
    -0.95
    ß
    -0.94
     referen
    -0.94
    ñ
    -0.93
     rall
    -0.92
    POSITIVE LOGITS
    co
    1.37
    me
    0.83
    nz
    0.80
    cc
    0.80
    toe
    0.80
    youtube
    0.78
    image
    0.78
    twitter
    0.78
    cs
    0.78
    static
    0.76
    Activations Density 0.007%

    No Known Activations