© 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. 2-RES-JB
    11. 23667
    Prev
    Next
    INDEX
    Explanations

    adjectives related to cleanliness or orderliness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "clean"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    framework
    -0.72
    amazon
    -0.71
    ivist
    -0.70
    study
    -0.66
    ically
    -0.64
    analy
    -0.64
    âĨij
    -0.64
    review
    -0.63
    looking
    -0.62
    ansas
    -0.62
    POSITIVE LOGITS
     tremend
    0.85
     legion
    0.73
    lehem
    0.71
    nai
    0.69
    ickle
    0.67
     Ambro
    0.67
    pload
    0.66
     Gong
    0.63
     Ange
    0.63
     Snapdragon
    0.63
    Activations Density 0.001%

    No Known Activations