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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 21396
    Prev
    Next
    INDEX
    Explanations

    words related to physical injuries and medical conditions in the body

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical conditions and 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
    ãĤ¤ãĥĪ
    -0.73
     sqor
    -0.69
    à¼
    -0.68
    fml
    -0.68
    ãĤ±
    -0.67
    ilet
    -0.67
    cash
    -0.66
    States
    -0.65
     Tradable
    -0.65
    Poké
    -0.63
    POSITIVE LOGITS
    rosis
    0.91
    bery
    0.75
    otomy
    0.75
     bleed
    0.70
     choke
    0.66
    itiz
    0.66
    bing
    0.66
     Canaver
    0.66
    cles
    0.63
    ader
    0.62
    Activations Density 0.239%

    No Known Activations