Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-RES-JB
    6. 10650
    Prev
    Next
    INDEX
    Explanations

    phrases or keywords related to advertising or marketing

    oai_token-act-pair · gpt-3.5-turbo

    words associated with marketing and promotion

    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
    hate
    -0.76
     annotations
    -0.70
    itia
    -0.69
    Material
    -0.69
     Drawing
    -0.68
     depos
    -0.68
     composing
    -0.67
     annotation
    -0.65
    ilipp
    -0.64
     Comments
    -0.63
    POSITIVE LOGITS
     advertised
    3.32
     touted
    2.90
     billed
    2.31
     marketed
    2.21
     advertise
    1.70
     promoted
    1.57
     touting
    1.52
     publicized
    1.45
    advert
    1.44
     trumpet
    1.43
    Activations Density 0.029%

    No Known Activations