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. 7-RES-JB
    6. 14846
    Prev
    Next
    INDEX
    Explanations

    text related to online advertising, specifically focusing on tracking cookies and ads

    oai_token-act-pair · gpt-3.5-turbo

    references to advertisements and related digital marketing concepts

    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
    otype
    -0.88
    bred
    -0.84
    lihood
    -0.81
    20439
    -0.79
    arity
    -0.72
    ĨĴ
    -0.71
    risome
    -0.67
     Presbyter
    -0.67
     Patriarch
    -0.67
    otypes
    -0.65
    POSITIVE LOGITS
    vertising
    1.18
    elaide
    0.97
    vertis
    0.94
     nause
    0.91
     blockers
    0.91
     blocker
    0.91
     ads
    0.85
     advertising
    0.83
     hoard
    0.82
    strip
    0.81
    Activations Density 0.023%

    No Known Activations