© 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. 20512
    Prev
    Next
    INDEX
    Explanations

    terms related to advertising and marketing strategies

    oai_token-act-pair · gpt-3.5-turbo

    references to marketing strategies and brand promotions

    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
    Plot
    -0.84
    UTC
    -0.79
     witnesses
    -0.78
    anon
    -0.78
    plementation
    -0.74
    ureau
    -0.73
     examiner
    -0.72
    Princ
    -0.70
    REP
    -0.70
    ENTION
    -0.70
    POSITIVE LOGITS
     products
    1.36
     brands
    1.26
     apparel
    1.24
     branded
    1.22
     fragrance
    1.17
    branded
    1.17
     merchandise
    1.15
     cosmetics
    1.11
     perfume
    1.10
     shampoo
    1.08
    Activations Density 0.418%

    No Known Activations