© 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. 10567
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to entertainment, such as movie titles, studios, and video game titles

    oai_token-act-pair · gpt-3.5-turbo

    names of game developers and related companies

    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
    heses
    -0.87
     rout
    -0.82
    etting
    -0.77
     retri
    -0.76
    hetic
    -0.75
    hesis
    -0.71
    ials
    -0.71
    rawdownloadcloneembedreportprint
    -0.70
     awoken
    -0.70
    enegger
    -0.70
    POSITIVE LOGITS
     Entertainment
    1.07
     Comics
    1.04
    Gear
    1.02
    Film
    1.01
    Circ
    0.98
    Movie
    0.98
    Zone
    0.97
     Studios
    0.97
    Beast
    0.95
    byte
    0.95
    Activations Density 0.202%

    No Known Activations