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

    Neuronpedia

    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. 2-RES-JB
    11. 23743
    Prev
    Next
    INDEX
    Explanations

    references to bones or bone-related terminology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bone health and medical conditions affecting bones

    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
    committee
    -0.71
    ersive
    -0.69
     Editorial
    -0.68
     Emerging
    -0.66
     Administrative
    -0.66
    erva
    -0.65
     Administ
    -0.65
    Dispatch
    -0.65
    NPR
    -0.65
     Policies
    -0.64
    POSITIVE LOGITS
     marrow
    1.64
    bone
    1.26
    Bone
    1.26
    bones
    1.12
     bone
    1.06
     fide
    1.05
     bones
    1.02
     Bone
    0.97
    bags
    0.93
    clad
    0.91
    Activations Density 0.007%

    No Known Activations