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. 0-RES-JB
    6. 9008
    Prev
    Next
    INDEX
    Explanations

    words related to bone and bone-related medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to bone-related terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Princ
    -0.77
     conduc
    -0.76
    markets
    -0.71
    quickShipAvailable
    -0.65
    Works
    -0.64
    PASS
    -0.64
     Guides
    -0.62
     Administrator
    -0.62
    abouts
    -0.62
     Anonymous
    -0.62
    POSITIVE LOGITS
     bone
    3.66
     Bone
    2.33
    bone
    2.33
     bones
    2.23
    Bone
    2.22
     marrow
    1.77
    bones
    1.58
     oste
    1.56
     fracture
    1.55
     tendon
    1.48
    Activations Density 0.009%

    No Known Activations