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. 0-RES-JB
    6. 22015
    Prev
    Next
    INDEX
    Explanations

    terms related to promotional activities or endorsements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "prom" and its variations, indicating a focus on promotional content or activities

    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
     adjusted
    -0.74
     Ort
    -0.70
     tilt
    -0.70
     detached
    -0.67
     melt
    -0.65
     Lang
    -0.65
     unit
    -0.64
     Index
    -0.64
     sink
    -0.63
     Units
    -0.62
    POSITIVE LOGITS
    prom
    4.12
    Prom
    2.60
     Prom
    1.83
     promotion
    1.34
     Promotion
    1.19
     promoter
    1.16
    del
    1.14
     prom
    1.12
     Promise
    1.11
     promoters
    1.11
    Activations Density 0.011%

    No Known Activations