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. 11-RES-JB
    6. 4490
    Prev
    Next
    INDEX
    Explanations

    pronouns and second person verb forms referring to the reader or user

    oai_token-act-pair · gpt-3.5-turbo

    references to user activity and interactions on the internet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hercules
    -0.75
     CLR
    -0.72
     prevailing
    -0.67
    breeding
    -0.66
    fell
    -0.64
    terness
    -0.63
    Ĭ±
    -0.63
     Excellence
    -0.61
     laure
    -0.61
     formulation
    -0.60
    POSITIVE LOGITS
     downloaded
    1.33
     login
    1.33
     upload
    1.30
     logged
    1.29
     browsing
    1.24
     browse
    1.24
     uploaded
    1.21
     downloading
    1.20
     download
    1.16
     encrypt
    1.14
    Activations Density 0.350%

    No Known Activations