© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14234
    Prev
    Next
    INDEX
    Explanations

    terms related to supervising, managing, organizing, or overseeing activities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    words related to supervision or oversight

    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
    tery
    -0.89
    ted
    -0.87
    DEN
    -0.81
    date
    -0.77
    lua
    -0.77
    blank
    -0.74
    pocket
    -0.74
    burning
    -0.72
    den
    -0.71
    mary
    -0.71
    POSITIVE LOGITS
     superv
    1.23
     oversee
    0.86
     conduc
    0.86
     overseeing
    0.81
     supervision
    0.80
    ises
    0.77
    isions
    0.75
    atts
    0.73
     adolesc
    0.73
     benefic
    0.72
    Activations Density 0.006%

    No Known Activations