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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 21404
    Prev
    Next
    INDEX
    Explanations

    terms related to bones or bone-related conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to bones and related medical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iott
    -0.76
    atcher
    -0.71
    inel
    -0.69
    ively
    -0.67
    Agent
    -0.66
    perture
    -0.66
    iating
    -0.66
     Observer
    -0.64
    ggles
    -0.64
     Opportun
    -0.63
    POSITIVE LOGITS
     marrow
    1.76
    bones
    1.10
    Bone
    1.07
     fide
    1.05
     bones
    1.03
     mineral
    1.02
     broth
    1.00
    bone
    0.99
     fractures
    0.98
     fracture
    0.93
    Activations Density 0.031%

    No Known Activations