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. 6-RES-JB
    6. 4842
    Prev
    Next
    INDEX
    Explanations

    adjectives describing something negative or unappealing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ugly" and its surrounding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingham
    -0.99
    iasm
    -0.97
    ership
    -0.95
    agall
    -0.95
    aver
    -0.91
    unes
    -0.89
    erve
    -0.86
    ularity
    -0.84
    akeru
    -0.82
    gravity
    -0.81
    POSITIVE LOGITS
     ugly
    1.07
     mole
    0.80
     surprises
    0.79
     adolesc
    0.78
     elephant
    0.78
     beasts
    0.78
     nasty
    0.76
     scar
    0.76
     fallout
    0.75
     crap
    0.74
    Activations Density 0.024%

    No Known Activations