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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18657
    Prev
    Next
    INDEX
    Explanations

    references to dead bodies or corpses

    oai_token-act-pair · gpt-3.5-turbo

    references to corpses and bodies in graphic or macabre contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orney
    -0.84
    itsch
    -0.76
    Americ
    -0.72
     Monthly
    -0.72
    itudes
    -0.69
     Berks
    -0.68
    rish
    -0.65
    ipolar
    -0.64
    Channel
    -0.64
    wana
    -0.63
    POSITIVE LOGITS
     corpses
    1.13
     carc
    1.09
     corpse
    1.07
     Corpse
    1.00
     slain
    0.82
     rotting
    0.81
     pile
    0.80
     Reaper
    0.77
     skulls
    0.77
    lly
    0.76
    Activations Density 0.034%

    No Known Activations