© 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. 0-RES-JB
    11. 11856
    Prev
    Next
    INDEX
    Explanations

    phrases related to fixtures or events

    oai_token-act-pair · gpt-3.5-turbo

    references to scheduled events or matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icy
    -0.72
     NS
    -0.66
    olicited
    -0.65
    assisted
    -0.63
     CC
    -0.63
    amn
    -0.62
     Kor
    -0.62
    ih
    -0.60
    onomous
    -0.60
     hugs
    -0.60
    POSITIVE LOGITS
     fixture
    3.88
     fixtures
    3.75
     fitt
    1.22
    ixture
    1.09
    ixtures
    1.07
     bulbs
    1.04
     marquee
    1.00
     CFL
    1.00
     staple
    0.98
     tenant
    0.97
    Activations Density 0.018%

    No Known Activations