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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 8072
    Prev
    Next
    INDEX
    Explanations

    references related to Harvard University

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Ivy League universities, particularly Harvard and Yale

    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
    ´
    -0.82
     armour
    -0.75
     trailers
    -0.72
     tyres
    -0.69
    addons
    -0.68
    è»
    -0.67
     recall
    -0.66
     pict
    -0.65
     recognise
    -0.64
    wra
    -0.63
    POSITIVE LOGITS
     Harvard
    3.50
     Yale
    2.51
     Princeton
    2.09
     Stanford
    1.99
     Dartmouth
    1.98
     MIT
    1.96
     Cornell
    1.85
     Cambridge
    1.84
     NYU
    1.82
     Georgetown
    1.75
    Activations Density 0.018%

    No Known Activations