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. 3-RES-JB
    6. 13830
    Prev
    Next
    INDEX
    Explanations

    references to a particular group of people, often referred to as "folks."

    oai_token-act-pair · gpt-3.5-turbo

    references to a group of people characterized as "folks"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Course
    -0.67
    Interstitial
    -0.65
    Weapon
    -0.63
    Accessory
    -0.63
    Prem
    -0.62
    Stre
    -0.62
    Prom
    -0.61
    Pakistan
    -0.61
     SER
    -0.60
    VL
    -0.60
    POSITIVE LOGITS
    folk
    0.94
    hots
    0.81
     folks
    0.80
     who
    0.77
    ometimes
    0.74
    around
    0.74
    kies
    0.73
    wagon
    0.72
    ingen
    0.72
    cape
    0.72
    Activations Density 0.012%

    No Known Activations