© 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. 0-RES-JB
    11. 22534
    Prev
    Next
    INDEX
    Explanations

    references to branding or rebranding activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "brand" or related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Intermediate
    -0.82
     intermediate
    -0.78
     Partial
    -0.73
     per
    -0.71
     anticip
    -0.70
     males
    -0.67
     holes
    -0.65
     inputs
    -0.65
     rec
    -0.65
     che
    -0.64
    POSITIVE LOGITS
    brand
    4.54
    branded
    2.09
    Brand
    1.88
     Brand
    1.49
     branding
    1.42
     brand
    1.40
     brands
    1.20
     branded
    1.12
    market
    1.07
    biz
    1.04
    Activations Density 0.016%

    No Known Activations