© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11447
    Prev
    Next
    INDEX
    Explanations

    names of historical and possibly military figures or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper names and titles related to historical figures or leaders

    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
    ebin
    -0.82
    awareness
    -0.76
    blogs
    -0.75
     selfie
    -0.74
     salsa
    -0.73
     esports
    -0.72
     selfies
    -0.72
     confir
    -0.72
    gencies
    -0.71
    Inside
    -0.71
    POSITIVE LOGITS
     Chamberlain
    1.34
     Hubbard
    1.28
     Harding
    1.26
     Howe
    1.25
     Thatcher
    1.23
     Byrd
    1.23
     Churchill
    1.22
     Hale
    1.21
     Roosevelt
    1.20
     Buchanan
    1.19
    Activations Density 0.321%

    No Known Activations