© 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. 9459
    Prev
    Next
    INDEX
    Explanations

    movie-related terms like "directed", "film", and "produced"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "directed" and related phrases about film production and ownership

    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
     inacc
    -0.68
    bra
    -0.67
     inability
    -0.66
    isms
    -0.66
    assies
    -0.63
    tro
    -0.62
    olver
    -0.62
     temptation
    -0.62
     stra
    -0.60
     footprints
    -0.60
    POSITIVE LOGITS
     by
    1.16
     jointly
    1.03
     BY
    0.99
    by
    0.96
    By
    0.84
     democratically
    0.81
     By
    0.79
    actionDate
    0.79
    ª
    0.78
    leased
    0.76
    Activations Density 0.149%

    No Known Activations