© 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. 3792
    Prev
    Next
    INDEX
    Explanations

    instances of the word "may" indicating a possibility or permission

    oai_token-act-pair · gpt-3.5-turbo

    the modal verb "may" indicating possibility or potential

    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
     Fighter
    -0.74
     LOT
    -0.71
     Desktop
    -0.67
    ocracy
    -0.66
     sacked
    -0.63
     Bul
    -0.61
     Enforcement
    -0.60
    pires
    -0.59
     Bus
    -0.58
     servant
    -0.58
    POSITIVE LOGITS
    nard
    0.99
     conclud
    0.99
    berra
    0.92
    hap
    0.90
    onna
    0.89
     ende
    0.87
     misunder
    0.81
     preced
    0.78
     derive
    0.78
     imply
    0.77
    Activations Density 0.043%

    No Known Activations