© 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. 1822
    Prev
    Next
    INDEX
    Explanations

    words related to Middle Eastern locations

    oai_token-act-pair · gpt-3.5-turbo

    words related to the Middle East

    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
    yip
    -0.87
    pared
    -0.85
    chy
    -0.81
    perty
    -0.81
    senal
    -0.78
    cci
    -0.76
    BuyableInstoreAndOnline
    -0.71
    pheus
    -0.70
    pton
    -0.69
    skirts
    -0.68
    POSITIVE LOGITS
    rophe
    1.06
    rophic
    1.04
    roph
    0.95
    ruct
    0.95
    rop
    0.88
    ast
    0.88
    rians
    0.85
    rup
    0.84
    ro
    0.82
    aur
    0.81
    Activations Density 0.012%

    No Known Activations