© 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. 8-RES-JB
    11. 9439
    Prev
    Next
    INDEX
    Explanations

    references to specific educational institutions, particularly universities

    oai_token-act-pair · gpt-3.5-turbo

    references to universities and legal associations in a particular state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.84
     Aires
    -0.70
     Moonlight
    -0.69
    pload
    -0.69
    nesday
    -0.63
     Guru
    -0.62
     Sleeping
    -0.62
     Jinn
    -0.61
     Stard
    -0.61
    Frames
    -0.60
    POSITIVE LOGITS
    hyde
    0.92
    sylvania
    0.87
     legislatures
    0.84
     troopers
    0.84
     trooper
    0.82
    aucuses
    0.76
    itol
    0.74
    sylv
    0.73
     lieutenant
    0.71
     Vera
    0.71
    Activations Density 0.170%

    No Known Activations