© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 9979
    Prev
    Next
    INDEX
    Explanations

    actions involving physical movements and interactions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to personal belongings or possessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVERS
    -0.87
    ablishment
    -0.76
    avid
    -0.73
    wik
    -0.72
    eus
    -0.72
     indirectly
    -0.70
    usive
    -0.69
    iliate
    -0.69
    onymous
    -0.67
    eless
    -0.67
    POSITIVE LOGITS
     clipboard
    1.02
     seat
    1.02
     cigarette
    0.96
     headset
    0.96
     flask
    0.95
     composure
    0.94
     customary
    0.93
     cane
    0.92
     bearings
    0.91
     wallet
    0.88
    Activations Density 0.264%

    No Known Activations