Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 15053
    Prev
    Next
    INDEX
    Explanations

    references to various devices or services related to media consumption like TV shows, streaming, and internet browsing

    oai_token-act-pair · gpt-3.5-turbo

    content related to streaming and media consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prag
    -0.72
     sheds
    -0.72
     capit
    -0.69
     Kear
    -0.68
     fences
    -0.68
     underest
    -0.68
    jah
    -0.67
    anthrop
    -0.67
     hat
    -0.67
     impl
    -0.67
    POSITIVE LOGITS
     multimedia
    1.24
     apps
    1.08
     DVDs
    1.03
     Netflix
    1.03
     music
    0.99
     desktop
    0.98
     iTunes
    0.97
     movies
    0.96
    VIDIA
    0.94
     browsing
    0.94
    Activations Density 0.612%

    No Known Activations