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. 0-RES-JB
    6. 23495
    Prev
    Next
    INDEX
    Explanations

    references to academic degrees, especially Ph.D

    oai_token-act-pair · gpt-3.5-turbo

    references to advanced academic degrees, particularly PhDs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     carriers
    -0.77
     carrier
    -0.76
    air
    -0.70
    othing
    -0.70
     cove
    -0.69
     Tire
    -0.67
    âĶĢâĶĢ
    -0.67
    Gar
    -0.66
    airs
    -0.65
    ize
    -0.63
    POSITIVE LOGITS
     PhD
    3.66
     doctoral
    2.57
     dissertation
    1.75
     MBA
    1.71
     MPH
    1.59
     undergraduate
    1.47
    doctoral
    1.47
     graduate
    1.39
     undergrad
    1.38
     Faculty
    1.29
    Activations Density 0.013%

    No Known Activations