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. 11954
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to the heart

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various health diseases and conditions, particularly cardiovascular issues

    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
    soDeliveryDate
    -0.99
    Reviewer
    -0.82
    ãĤ±
    -0.81
    VALUE
    -0.77
    ilet
    -0.75
    åº
    -0.74
    idge
    -0.73
    oos
    -0.73
    é¾
    -0.72
    xtap
    -0.71
    POSITIVE LOGITS
    rosis
    1.03
     diagnoses
    0.96
     diagnosis
    0.94
    mia
    0.85
     disease
    0.84
     disorders
    0.84
     prevention
    0.82
    clerosis
    0.82
     dementia
    0.82
     depression
    0.81
    Activations Density 0.035%

    No Known Activations