© 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. 10-RES-JB
    11. 8239
    Prev
    Next
    INDEX
    Explanations

    terms related to temporary or impromptu events or structures, often associated with culture or technology like pop-up shops or events

    oai_token-act-pair · gpt-3.5-turbo

    references to "pop-up" events or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¿½
    -0.69
     Howe
    -0.67
     Ri
    -0.61
     tightly
    -0.61
     elector
    -0.61
     scant
    -0.60
     Duc
    -0.60
     adject
    -0.60
     Dos
    -0.60
     hus
    -0.60
    POSITIVE LOGITS
    ups
    1.19
    up
    1.17
    culture
    1.04
    shots
    1.02
    out
    1.00
    based
    0.99
    science
    0.96
    psych
    0.92
    art
    0.91
    filled
    0.90
    Activations Density 0.044%

    No Known Activations