© 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. 3179
    Prev
    Next
    INDEX
    Explanations

    terms related to dictionaries

    oai_token-act-pair · gpt-3.5-turbo

    references to dictionaries and definitions

    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
    ments
    -0.86
    mented
    -0.77
    arnaev
    -0.71
    vertising
    -0.70
    urion
    -0.70
     Antar
    -0.69
    meat
    -0.68
    cedented
    -0.67
    warm
    -0.66
    anced
    -0.64
    POSITIVE LOGITS
     Dictionary
    1.31
     dictionary
    1.07
     definitions
    0.97
     textbook
    0.94
    initions
    0.91
     Encyclopedia
    0.91
    pedia
    0.90
     Britann
    0.89
    ictionary
    0.85
    reference
    0.84
    Activations Density 0.088%

    No Known Activations