© 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. 3-RES-JB
    11. 12299
    Prev
    Next
    INDEX
    Explanations

    the word "small."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "small" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raints
    -0.68
    ILLE
    -0.67
    Favorite
    -0.66
    æѦ
    -0.65
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.65
    roit
    -0.65
    ++++++++++++++++
    -0.65
    alin
    -0.65
    ————————————————
    -0.64
    èĥ
    -0.64
    POSITIVE LOGITS
    pox
    1.14
     consolation
    1.00
     intestine
    0.98
     sized
    0.91
     fry
    0.90
     handful
    0.88
     batches
    0.84
     fraction
    0.81
    hearted
    0.81
     insignificant
    0.78
    Activations Density 0.024%

    No Known Activations