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. 8-RES-JB
    6. 18933
    Prev
    Next
    INDEX
    Explanations

    instances where something is described as a specific type of person

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uden
    -0.77
    Events
    -0.74
    scenes
    -0.72
    icides
    -0.71
    edit
    -0.69
     appointments
    -0.68
    mares
    -0.68
     assemblies
    -0.68
     Elections
    -0.68
    breaks
    -0.68
    POSITIVE LOGITS
     member
    1.05
     spectator
    1.03
     believer
    0.99
    verse
    0.97
     hypocr
    0.96
     participant
    0.95
     teenager
    0.93
     follower
    0.92
     prisoner
    0.91
     citizen
    0.89
    Activations Density 0.163%

    No Known Activations