© 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. 7-RES-JB
    11. 23691
    Prev
    Next
    INDEX
    Explanations

    terms related to audience or television viewership

    oai_token-act-pair · gpt-3.5-turbo

    mentions of viewers and their engagement with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alz
    -0.73
     Bain
    -0.68
    ulic
    -0.67
     Shotgun
    -0.65
     Bicycle
    -0.61
    agna
    -0.60
     contingency
    -0.60
     Ski
    -0.58
     Surgery
    -0.57
    apa
    -0.57
    POSITIVE LOGITS
     viewers
    0.93
     tuned
    0.88
    erv
    0.87
     largeDownload
    0.84
     viewership
    0.83
    hip
    0.80
    feed
    0.78
     wat
    0.77
     watching
    0.77
    cript
    0.76
    Activations Density 0.027%

    No Known Activations