© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2629
    Prev
    Next
    INDEX
    Explanations

    words related to physiological processes and medical conditions, such as vascular dysfunction and cell proliferation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vascular conditions and cellular processes

    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
    soDeliveryDate
    -0.86
    ãĥĩãĤ£
    -0.76
    iquette
    -0.71
    ãĤ±
    -0.69
    kit
    -0.66
    ãĤ¢ãĥ«
    -0.64
    wered
    -0.64
    riad
    -0.64
    ourt
    -0.64
    selage
    -0.63
    POSITIVE LOGITS
     phenotype
    0.98
    llular
    0.94
     biomark
    0.94
     disorder
    0.90
     disorders
    0.89
    opathy
    0.88
     phen
    0.87
     lesions
    0.87
     inhibition
    0.86
     susceptibility
    0.85
    Activations Density 0.318%

    No Known Activations