© 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. 4-RES-JB
    11. 17096
    Prev
    Next
    INDEX
    Explanations

    verbs ending in 'ks'

    oai_token-act-pair · gpt-3.5-turbo

    specific sequences of letters or sounds, particularly common suffixes and variations

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

    No Comments

    Negative Logits
    )=(
    -0.73
    å°Ĩ
    -0.65
     Frie
    -0.60
    zona
    -0.57
    wcsstore
    -0.57
     FSA
    -0.57
     brim
    -0.57
     Ples
    -0.56
     Hemp
    -0.56
     Rove
    -0.55
    POSITIVE LOGITS
    edu
    1.01
    hai
    0.91
    ji
    0.70
    uthor
    0.69
    jee
    0.67
    irs
    0.67
    hower
    0.65
    li
    0.64
    jin
    0.62
    istan
    0.62
    Activations Density 0.346%

    No Known Activations