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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 15032
    Prev
    Next
    INDEX
    Explanations

    medical terms related to the examination and evaluation of health status, such as 'physician assessment', 'health', and 'participant reported health'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical assessments and machinery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hots
    -0.81
    hemy
    -0.71
    awatts
    -0.68
    uits
    -0.68
    htaking
    -0.68
    awed
    -0.67
    taboola
    -0.65
    ĵĺ
    -0.64
    âĢİ
    -0.63
    CLASSIFIED
    -0.62
    POSITIVE LOGITS
     phenotype
    0.80
    scape
    0.78
     specification
    0.71
     compartment
    0.71
     nucleus
    0.71
     descriptor
    0.70
    ificate
    0.70
     afterwards
    0.69
     portion
    0.67
    worthiness
    0.66
    Activations Density 0.785%

    No Known Activations