© 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. 9-RES-JB
    11. 15607
    Prev
    Next
    INDEX
    Explanations

    phrases related to small groups or quantities

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "small."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emis
    -0.70
    reon
    -0.69
    ilee
    -0.65
    ources
    -0.64
     Builder
    -0.62
    rob
    -0.62
    YR
    -0.61
    emy
    -0.61
    alin
    -0.59
     Indra
    -0.59
    POSITIVE LOGITS
    pox
    1.38
     intestine
    1.03
     handful
    0.97
     fry
    0.89
    folk
    0.87
     amount
    0.87
    ish
    0.87
     consolation
    0.86
     sized
    0.86
     percentage
    0.85
    Activations Density 0.050%

    No Known Activations