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. 4-RES-JB
    6. 23756
    Prev
    Next
    INDEX
    Explanations

    phrases related to advertising and promotional material

    oai_token-act-pair · gpt-3.5-turbo

    mentions and discussions related to advertising

    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
    izabeth
    -0.82
    akia
    -0.82
    borg
    -0.78
     stride
    -0.70
    cipline
    -0.69
     dilig
    -0.68
    tsky
    -0.67
    otom
    -0.67
     orbital
    -0.64
    oslav
    -0.63
    POSITIVE LOGITS
     Gleaming
    0.91
     Merch
    0.79
     Discount
    0.72
     Selling
    0.71
     merch
    0.68
    Sales
    0.68
    Prom
    0.68
     advertise
    0.68
    vertisement
    0.66
     Sales
    0.66
    Activations Density 0.464%

    No Known Activations