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. 2-RES-JB
    6. 3455
    Prev
    Next
    INDEX
    Explanations

    the word "pretty" used in a positive context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pretty" used as an intensifier

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venant
    -0.90
    iment
    -0.82
    arta
    -0.76
    aer
    -0.73
    iments
    -0.72
    PLIED
    -0.72
    pent
    -0.72
    JV
    -0.71
    upon
    -0.69
    ipper
    -0.68
    POSITIVE LOGITS
     darn
    0.98
     harmless
    0.86
     nifty
    0.84
     hairy
    0.80
     snipp
    0.76
     damn
    0.75
     innocuous
    0.75
     noses
    0.75
     miserable
    0.74
     ugly
    0.71
    Activations Density 0.018%

    No Known Activations