© 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. 3903
    Prev
    Next
    INDEX
    Explanations

    capital letters followed by numbers, potentially indicating headers or sections in a document

    oai_token-act-pair · gpt-3.5-turbo

    instances of high numerical values or scores

    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
    uca
    -0.86
    aterasu
    -0.81
    xual
    -0.79
     dissu
    -0.75
    ertodd
    -0.74
     scrap
    -0.74
    aviour
    -0.74
     detract
    -0.72
    byss
    -0.72
    utic
    -0.72
    POSITIVE LOGITS
    ccording
    0.98
    ³³³³³³³³³³³³³³³³
    0.92
    Posted
    0.89
    Guest
    0.82
    Recent
    0.81
    Introduction
    0.79
    ³³³³
    0.79
     Related
    0.77
    Latest
    0.77
    Using
    0.76
    Activations Density 0.464%

    No Known Activations