© 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 EvalsExportsinterp-engineNEWAPI 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. 18930
    Prev
    Next
    INDEX
    Explanations

    terms related to human bones and medical conditions related to bones

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with bones and bone-related conditions

    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
    ilts
    -0.76
    atcher
    -0.75
    iott
    -0.74
    inel
    -0.72
    Agent
    -0.70
    iating
    -0.70
    olitan
    -0.68
    ionage
    -0.67
    ilities
    -0.66
    antis
    -0.66
    POSITIVE LOGITS
     marrow
    1.72
    bones
    1.11
    Bone
    1.11
     fide
    1.11
     broth
    1.10
    bone
    1.06
     mineral
    1.03
     bones
    1.02
     collagen
    0.93
     fractures
    0.89
    Activations Density 0.027%

    No Known Activations