Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 2763
    Prev
    Next
    INDEX
    Explanations

    references to dead bodies or corpses

    oai_token-act-pair · gpt-3.5-turbo

    references to corpses and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bidden
    -0.69
    chie
    -0.69
    amaru
    -0.65
    orney
    -0.65
    axis
    -0.63
     interests
    -0.63
    MODE
    -0.62
    Bah
    -0.62
    mable
    -0.62
     Monthly
    -0.62
    POSITIVE LOGITS
     coffin
    1.14
     corpse
    1.11
     carc
    1.06
     Corpse
    1.02
     heap
    0.93
     corpses
    0.92
     Coffin
    0.91
     ashes
    0.85
     crem
    0.80
     bury
    0.78
    Activations Density 0.036%

    No Known Activations