© 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. 10-RES-JB
    11. 2863
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in the writing and directing of various works

    oai_token-act-pair · gpt-3.5-turbo

    information about the creators and contributors of a film or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gdala
    -0.82
    yip
    -0.81
    ilege
    -0.75
    obyl
    -0.75
    hunt
    -0.73
     impunity
    -0.72
    Merit
    -0.71
     snowball
    -0.71
    ratom
    -0.67
    daq
    -0.66
    POSITIVE LOGITS
     screenplay
    1.40
     Producer
    1.26
     narration
    1.24
     composer
    1.24
     Editing
    1.20
    writer
    1.18
     cinem
    1.18
     producer
    1.17
     editing
    1.17
     lyric
    1.15
    Activations Density 0.274%

    No Known Activations