© 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. 2562
    Prev
    Next
    INDEX
    Explanations

    terms related to idiocy or foolishness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "idiocy" and related terms indicating foolishness or lack of intelligence

    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
     sparks
    -0.69
     sentences
    -0.66
     short
    -0.65
     Bond
    -0.65
     contracted
    -0.65
     shortened
    -0.63
     sentence
    -0.63
     Stadium
    -0.63
     capacity
    -0.61
     quick
    -0.61
    POSITIVE LOGITS
    olith
    2.57
    olithic
    2.48
    osphere
    2.25
    ocy
    2.18
    ophy
    2.09
    ogeneous
    2.06
    otype
    2.01
    odynamics
    2.00
    ogenous
    1.99
    ogeneity
    1.94
    Activations Density 0.023%

    No Known Activations