© 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. 0-RES-JB
    11. 2295
    Prev
    Next
    INDEX
    Explanations

    the word "lump."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "lump" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cu
    -0.73
    ires
    -0.71
    ande
    -0.67
    Domin
    -0.64
     Schmidt
    -0.63
    OPE
    -0.63
     Bravo
    -0.62
    oute
    -0.61
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.61
    Press
    -0.61
    POSITIVE LOGITS
     lump
    3.82
     Lump
    1.87
    alog
    1.13
     grouped
    0.96
     misrepresent
    0.95
     stereotyp
    0.86
     pigeon
    0.85
     bump
    0.84
     opportun
    0.82
     blob
    0.81
    Activations Density 0.021%

    No Known Activations