Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3-RES-JB
    6. 22048
    Prev
    Next
    INDEX
    Explanations

    words related to physical injuries, such as sprains

    oai_token-act-pair · gpt-3.5-turbo

    references to sprains and related injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.90
     Passage
    -0.72
    ocene
    -0.70
    uliffe
    -0.69
     Defenders
    -0.67
    uyomi
    -0.67
    EStream
    -0.65
    ogun
    -0.65
    galitarian
    -0.65
    Reviewer
    -0.65
    POSITIVE LOGITS
    outed
    0.98
    outing
    0.96
    acer
    0.94
     spr
    0.93
    inters
    0.87
    atters
    0.84
    itely
    0.81
    ars
    0.80
    atche
    0.80
    ain
    0.79
    Activations Density 0.006%

    No Known Activations