© 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. 7-RES-JB
    11. 17226
    Prev
    Next
    INDEX
    Explanations

    words related to marketing

    oai_token-act-pair · gpt-3.5-turbo

    references to marketing and its strategies

    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
     Fas
    -0.83
    inite
    -0.75
     Templar
    -0.75
     captcha
    -0.72
     Carbuncle
    -0.70
     Judges
    -0.66
     Brah
    -0.65
    assian
    -0.65
     Sul
    -0.64
    ropy
    -0.63
    POSITIVE LOGITS
     campaigns
    0.91
     ploy
    0.89
    strip
    0.81
    verts
    0.80
     gimm
    0.80
    ONSORED
    0.78
     gimmick
    0.78
     slogan
    0.78
     blitz
    0.76
     hype
    0.76
    Activations Density 0.043%

    No Known Activations