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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 4898
    Prev
    Next
    INDEX
    Explanations

    references to Purdue University

    oai_token-act-pair · gpt-3.5-turbo

    mentions of educational institutions, particularly Purdue University and places associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reef
    -0.84
     metic
    -0.77
    ural
    -0.75
    epad
    -0.75
    */(
    -0.71
    abases
    -0.71
     nets
    -0.70
    hun
    -0.70
    emis
    -0.70
    icator
    -0.67
    POSITIVE LOGITS
     Blooming
    1.11
     Lafayette
    0.95
     Yates
    0.91
    SourceFile
    0.90
    urdue
    0.90
     Purdue
    0.87
     Dum
    0.82
    anne
    0.80
    aign
    0.78
    ulton
    0.78
    Activations Density 0.017%

    No Known Activations