© 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. 1-RES-JB
    11. 23958
    Prev
    Next
    INDEX
    Explanations

    capital letter sequences followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to companies or organizations, particularly in the entertainment and media sectors

    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
    bury
    -0.84
    aday
    -0.81
    atell
    -0.80
    Applications
    -0.78
    twitch
    -0.76
    ply
    -0.75
    andro
    -0.75
    ippi
    -0.74
    quote
    -0.73
    peer
    -0.72
    POSITIVE LOGITS
    MG
    0.99
     MG
    0.98
    BG
    0.94
    MT
    0.91
    allery
    0.88
    ENE
    0.88
    roup
    0.87
    roups
    0.81
    UGE
    0.80
    ERG
    0.78
    Activations Density 0.015%

    No Known Activations