© 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. 10-RES-JB
    6. 17511
    Prev
    Next
    INDEX
    Explanations

    mentions of universities and specific academic institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various state universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arded
    -0.81
    ardless
    -0.72
    ãĥķãĤ¡
    -0.72
    arding
    -0.72
    ard
    -0.69
    ï¸ı
    -0.65
    edin
    -0.64
    inav
    -0.64
    tm
    -0.64
    rative
    -0.63
    POSITIVE LOGITS
     University
    1.21
     Patrol
    1.10
     Trooper
    1.00
     Legislature
    0.99
     Univ
    0.97
     Semin
    0.92
     Senator
    0.88
    wide
    0.84
     Prison
    0.82
     Representative
    0.81
    Activations Density 0.036%

    No Known Activations