© 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. 12004
    Prev
    Next
    INDEX
    Explanations

    words related to places or organizations with the word "Det" as part of their name

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "Det" and its context within the text

    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
    advertising
    -0.74
    ragon
    -0.73
    print
    -0.68
     reproduction
    -0.68
     arithmetic
    -0.67
    otype
    -0.64
    capital
    -0.64
    ãĥ¼ãĤ¯
    -0.64
    ango
    -0.63
     kosher
    -0.62
    POSITIVE LOGITS
     Det
    3.60
    det
    1.24
     DET
    1.21
     det
    1.20
    Det
    1.09
     Detail
    1.08
     detachment
    1.02
     Dep
    1.00
     Capt
    0.95
     Sgt
    0.94
    Activations Density 0.007%

    No Known Activations