© 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. 0-RES-JB
    11. 1200
    Prev
    Next
    INDEX
    Explanations

    mentions of marketing strategies or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to marketing practices and strategies

    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
     Bash
    -0.78
    iffs
    -0.72
    Äĩ
    -0.69
    strate
    -0.68
     Appears
    -0.67
     peacefully
    -0.67
    zan
    -0.66
    ERAL
    -0.65
    itzer
    -0.65
    ridge
    -0.65
    POSITIVE LOGITS
     marketing
    3.57
     Marketing
    2.61
     marketers
    2.44
     advertising
    2.16
     promotional
    1.86
     marketed
    1.73
     branding
    1.73
     Advertising
    1.61
     sales
    1.54
    Sales
    1.46
    Activations Density 0.014%

    No Known Activations