© 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. 7332
    Prev
    Next
    INDEX
    Explanations

    locations or geographic references

    oai_token-act-pair · gpt-3.5-turbo

    references to location and timing in relation to events

    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
    poon
    -0.52
    cel
    -0.51
    ï¸ı
    -0.50
    agy
    -0.48
    DragonMagazine
    -0.48
    ¶
    -0.48
    quiet
    -0.46
    edly
    -0.46
    coon
    -0.45
     swe
    -0.45
    POSITIVE LOGITS
     Carbuncle
    0.55
    ividual
    0.49
    idges
    0.47
    aeda
    0.46
    ikers
    0.46
     Commissioners
    0.46
    ignt
    0.45
    orld
    0.45
    swick
    0.44
    اÙĦ
    0.44
    Activations Density 1.963%

    No Known Activations