© 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. 11-RES-JB
    11. 7616
    Prev
    Next
    INDEX
    Explanations

    information related to television shows and episodes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific television episodes and seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fax
    -0.80
    yip
    -0.77
    urat
    -0.77
    TeX
    -0.75
    imir
    -0.73
    Lenin
    -0.70
     racket
    -0.68
     Wah
    -0.67
    enment
    -0.67
     Yamaha
    -0.67
    POSITIVE LOGITS
     episodes
    1.55
     Season
    1.51
    episode
    1.50
    Season
    1.46
     episode
    1.45
     season
    1.39
     Emmy
    1.38
     sitcom
    1.38
     seasons
    1.36
    season
    1.36
    Activations Density 0.924%

    No Known Activations