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. 17426
    Prev
    Next
    INDEX
    Explanations

    instances of the word "oneself" used in sentences related to personal development or self-help

    oai_token-act-pair · gpt-3.5-turbo

    references to self-care and individual responsibility

    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
    ulet
    -0.66
     Fixes
    -0.57
     pals
    -0.56
    mitt
    -0.54
    earances
    -0.54
     Clean
    -0.53
     Scot
    -0.53
    orie
    -0.52
    ointed
    -0.52
    cher
    -0.52
    POSITIVE LOGITS
     oneself
    2.74
     itself
    2.62
     themselves
    1.54
     herself
    1.41
     himself
    1.32
     Himself
    1.19
    Secondly
    1.17
    undle
    1.16
     Secondly
    1.16
     Yourself
    1.15
    Activations Density 0.025%

    No Known Activations