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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10762
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of fractures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bone fractures and related injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hee
    -0.79
    agos
    -0.77
    dog
    -0.76
    sey
    -0.76
    worth
    -0.72
    atered
    -0.69
    pass
    -0.68
    fund
    -0.67
    oi
    -0.65
    ging
    -0.65
    POSITIVE LOGITS
    Downloadha
    0.99
     fractures
    0.96
     fracture
    0.86
    088
    0.83
    olars
    0.81
     Fract
    0.79
    ittal
    0.78
     fracturing
    0.75
    Rated
    0.73
    doms
    0.71
    Activations Density 0.066%

    No Known Activations