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. 7-RES-JB
    6. 18519
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of young individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals described by their age and notable characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.99
    ernels
    -0.97
     Machines
    -0.90
    rencies
    -0.89
    Frames
    -0.88
     Cups
    -0.86
     detectors
    -0.86
    ptoms
    -0.86
    apps
    -0.86
    ieties
    -0.85
    POSITIVE LOGITS
     classmate
    1.00
     woman
    0.99
     colleague
    0.96
     member
    0.90
     staffer
    0.90
     batch
    0.87
     couple
    0.86
     group
    0.86
     chunk
    0.85
     Romanian
    0.85
    Activations Density 0.320%

    No Known Activations