© 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. 13154
    Prev
    Next
    INDEX
    Explanations

    names or phrases containing "Les"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Les"

    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
    oted
    -0.79
    ACTED
    -0.77
    perial
    -0.74
    ITED
    -0.68
    tained
    -0.67
    serving
    -0.67
    OWS
    -0.65
    acca
    -0.63
    unct
    -0.63
     distributed
    -0.62
    POSITIVE LOGITS
    bians
    1.14
     Les
    0.98
    bia
    0.94
    bian
    0.92
    alog
    0.91
    nar
    0.88
    terness
    0.80
    earchers
    0.79
    bys
    0.79
    wana
    0.78
    Activations Density 0.005%

    No Known Activations