© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 466
    Prev
    Next
    INDEX
    Explanations

    words related to online advertising, tracking, and privacy concerns

    oai_token-act-pair · gpt-3.5-turbo

    words associated with online tracking and advertising technology

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

    No Comments

    Negative Logits
    esan
    -0.74
     Quart
    -0.73
    STD
    -0.73
     ceremonial
    -0.72
    urdue
    -0.71
    sonian
    -0.70
     Starfleet
    -0.70
    llan
    -0.69
    ajor
    -0.68
    hran
    -0.67
    POSITIVE LOGITS
    vertisement
    1.13
     ads
    1.11
     cookies
    1.10
     spam
    1.08
     SEO
    1.06
    stitial
    1.03
     advertising
    1.03
     advertisements
    0.98
     advertisers
    0.96
     bots
    0.96
    Activations Density 0.314%

    No Known Activations