© 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. 4-RES-JB
    11. 10594
    Prev
    Next
    INDEX
    Explanations

    specific mentions of educational institutions, particularly the Massachusetts Institute of Technology (MIT)

    oai_token-act-pair · gpt-3.5-turbo

    references to prestigious educational institutions and their associated technology programs

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

    No Comments

    Negative Logits
    onymous
    -0.84
    iewicz
    -0.78
    wp
    -0.72
    76561
    -0.69
    ppings
    -0.68
    azon
    -0.66
    cot
    -0.66
    emonic
    -0.66
    hash
    -0.65
    alog
    -0.64
    POSITIVE LOGITS
    Crunch
    0.89
     Technology
    0.87
     Solutions
    0.87
    icum
    0.82
     Excellence
    0.80
     Assessment
    0.78
    onomy
    0.77
    GROUP
    0.75
     Innovation
    0.74
     Identification
    0.73
    Activations Density 0.018%

    No Known Activations