© 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. 11274
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to land ownership and territorial disputes

    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
    ople
    -0.72
    aple
    -0.68
    erton
    -0.67
    ENG
    -0.64
     Pett
    -0.63
    aldi
    -0.63
    ilies
    -0.62
    aly
    -0.62
    activation
    -0.61
    omical
    -0.60
    POSITIVE LOGITS
    creen
    1.04
    hips
    0.90
    hell
    0.90
    hirt
    0.89
    bucks
    0.87
    cence
    0.87
    pace
    0.84
    paces
    0.84
    pring
    0.83
    heet
    0.82
    Activations Density 0.041%

    No Known Activations