© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 7663
    Prev
    Next
    INDEX
    Explanations

    mentions of burial sites or incidents involving graves

    oai_token-act-pair · gpt-3.5-turbo

    references to graves or burial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ack
    -0.75
    BuyableInstoreAndOnline
    -0.74
    ivity
    -0.74
     lawy
    -0.66
    ECA
    -0.65
    Bey
    -0.65
    ILA
    -0.64
     Deng
    -0.64
    isconsin
    -0.64
    nesota
    -0.63
    POSITIVE LOGITS
    lly
    1.29
    stones
    1.03
    lain
    0.95
     robbing
    0.92
     robbers
    0.89
    grave
    0.87
     mound
    0.83
    stone
    0.83
     grave
    0.82
    lands
    0.82
    Activations Density 0.041%

    No Known Activations