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. 20717
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions related to bone injuries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bone fractures or physical injuries

    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
     VW
    -0.74
     ãģ
    -0.73
     Santa
    -0.71
    eno
    -0.71
     Muller
    -0.71
    advertising
    -0.69
     Bunny
    -0.68
     Utility
    -0.67
    uni
    -0.66
     Hort
    -0.65
    POSITIVE LOGITS
     fracture
    3.32
     fracturing
    3.29
     fractures
    3.27
     fractured
    3.18
     Fract
    2.07
     fragmented
    2.01
     fragmentation
    1.88
     rupture
    1.85
     fragment
    1.79
     rupt
    1.75
    Activations Density 0.039%

    No Known Activations