© 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. 7187
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names within text

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and institutions

    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
     Bes
    -0.84
     Berks
    -0.79
     Bro
    -0.78
     Wass
    -0.78
     WA
    -0.77
     COURT
    -0.76
     Tues
    -0.74
     Walters
    -0.74
     Barth
    -0.73
     Schwarz
    -0.73
    POSITIVE LOGITS
    ip
    1.41
    ile
    1.38
    IP
    1.35
    ih
    1.25
    ib
    1.25
    iped
    1.20
    ilic
    1.20
    ipe
    1.20
    il
    1.20
    ir
    1.19
    Activations Density 0.173%

    No Known Activations