© 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. 17831
    Prev
    Next
    INDEX
    Explanations

    specific technical terms or concepts related to computer science and technology

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to technical or scientific concepts

    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
    theless
    -0.99
    stellar
    -0.75
    nian
    -0.72
     acknow
    -0.68
     eth
    -0.68
    FUL
    -0.66
     dressed
    -0.65
     interchange
    -0.64
    nz
    -0.64
     mus
    -0.62
    POSITIVE LOGITS
    istries
    0.98
    iciency
    0.96
    alyses
    0.95
    uctions
    0.91
    rors
    0.89
    acts
    0.87
    atives
    0.86
    verages
    0.86
    manac
    0.85
    ction
    0.85
    Activations Density 0.236%

    No Known Activations