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

    Neuronpedia

    Jacobian LensNEW
    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. 3272
    Prev
    Next
    INDEX
    Explanations

    mentions of finding objects or remains in various locations

    oai_token-act-pair · gpt-3.5-turbo

    references to discoveries or findings related to bodies or remains

    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
    thood
    -0.78
     incumb
    -0.73
    speak
    -0.72
    !/
    -0.69
    lect
    -0.69
     understands
    -0.68
    CEO
    -0.68
     expects
    -0.67
    HCR
    -0.67
     assumes
    -0.66
    POSITIVE LOGITS
     bushes
    1.33
     wreckage
    1.22
     woods
    1.21
     rubble
    1.17
     graves
    1.16
     landfill
    1.11
     rubbish
    1.11
     attic
    1.09
     woodland
    1.05
     creek
    1.03
    Activations Density 0.219%

    No Known Activations