© 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. 11173
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to deceased individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to bodies and remains, particularly in contexts of discovery and death

    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
    ipolar
    -0.90
     GPIO
    -0.75
     Opportun
    -0.74
    æ©Ł
    -0.72
    umar
    -0.67
    Bey
    -0.66
    isexual
    -0.66
    yg
    -0.66
    OY
    -0.65
    BuyableInstoreAndOnline
    -0.65
    POSITIVE LOGITS
     crem
    1.15
     burial
    1.09
     washed
    1.00
     recovered
    0.97
     decom
    0.97
     inciner
    0.96
     coffin
    0.95
     pile
    0.93
     buried
    0.91
     corpse
    0.91
    Activations Density 0.067%

    No Known Activations