© 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. 22164
    Prev
    Next
    INDEX
    Explanations

    references to specific names or locations, particularly those related to Eastern European culture

    oai_token-act-pair · gpt-3.5-turbo

    names or references to people and places, particularly those associated with the name "Savile" and related terms

    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
     threaded
    -0.71
     deaf
    -0.70
     bom
    -0.70
    WAYS
    -0.69
    hower
    -0.68
     slee
    -0.68
    Reloaded
    -0.68
     inclined
    -0.65
     filament
    -0.64
     proximity
    -0.64
    POSITIVE LOGITS
    ille
    1.08
    inelli
    1.08
    iour
    1.01
    Sav
    1.00
    anas
    0.96
    annah
    0.92
    itri
    0.91
    chenko
    0.91
    illas
    0.91
    vy
    0.91
    Activations Density 0.007%

    No Known Activations