© 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. 11314
    Prev
    Next
    INDEX
    Explanations

    references to specific cemeteries, particularly Arlington National Cemetery

    oai_token-act-pair · gpt-3.5-turbo

    references to specific cemeteries and burial-related terms

    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
    ï¸ı
    -0.79
    âĶ
    -0.76
    GL
    -0.70
    ados
    -0.70
    bart
    -0.69
    flex
    -0.68
    IRO
    -0.68
    ZZ
    -0.67
     Flex
    -0.66
    Python
    -0.66
    POSITIVE LOGITS
     Cemetery
    3.28
     cemetery
    3.17
     burial
    2.93
     graves
    2.55
     graveyard
    2.35
     crem
    2.19
     funer
    2.14
     funeral
    1.99
    emetery
    1.89
     coffin
    1.88
    Activations Density 0.045%

    No Known Activations