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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 20863
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to blood vessels and arterial health

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to vascular health and blood circulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -+-+-+-+
    -0.76
    asted
    -0.71
    berman
    -0.71
    udeb
    -0.70
    gradation
    -0.67
    eanor
    -0.65
    ocking
    -0.63
    onom
    -0.63
    heon
    -0.62
    arb
    -0.61
    POSITIVE LOGITS
     endot
    0.84
    lia
    0.83
    gins
    0.73
    lv
    0.72
    terness
    0.71
    bil
    0.70
    lain
    0.70
     Vessel
    0.69
    riel
    0.68
     vessels
    0.68
    Activations Density 0.116%

    No Known Activations