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

    Neuronpedia

    Jacobian LensNEW
    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. 11104
    Prev
    Next
    INDEX
    Explanations

    words related to instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to specific objects or concepts across various contexts

    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
    rooms
    -0.97
    sites
    -0.96
    bats
    -0.94
    paces
    -0.86
    azes
    -0.84
    classes
    -0.84
    types
    -0.83
    issues
    -0.82
    drops
    -0.81
    ongs
    -0.81
    POSITIVE LOGITS
     consisting
    0.92
     inhibitor
    0.88
     standpoint
    0.87
     approximation
    0.85
     diploma
    0.85
     affair
    0.84
     jumper
    0.84
     replica
    0.84
     ensued
    0.83
     mentality
    0.80
    Activations Density 0.505%

    No Known Activations