© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 22814
    Prev
    Next
    INDEX
    Explanations

    keywords related to MFA (Master of Fine Arts) programs

    oai_token-act-pair · gpt-3.5-turbo

    references to Master of Fine Arts (MFA) programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Trend
    -0.73
    swing
    -0.70
     Lizard
    -0.70
    tie
    -0.68
     Views
    -0.65
     Horton
    -0.65
     Spread
    -0.64
    come
    -0.64
    saw
    -0.63
    draw
    -0.62
    POSITIVE LOGITS
    FA
    1.26
    CLA
    0.94
    uthor
    0.88
    ogl
    0.81
    ZE
    0.80
    FF
    0.80
    ITH
    0.78
    ILS
    0.76
    ULTS
    0.76
    SPA
    0.75
    Activations Density 0.003%

    No Known Activations