© 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. 10-RES-JB
    11. 16022
    Prev
    Next
    INDEX
    Explanations

    physical attributes or markings on objects or individuals

    oai_token-act-pair · gpt-3.5-turbo

    descriptive terms associated with physical marks and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quotas
    -0.68
     Cosponsors
    -0.67
     duties
    -0.66
     logistics
    -0.63
     Costs
    -0.63
     repertoire
    -0.63
     schedules
    -0.62
     collaborations
    -0.62
     Standards
    -0.61
     partnerships
    -0.60
    POSITIVE LOGITS
     protr
    1.21
     etched
    1.08
     underneath
    1.07
     resembling
    0.99
     beneath
    0.98
     indicating
    0.97
     emanating
    0.94
     visible
    0.91
     sticking
    0.88
     around
    0.87
    Activations Density 0.272%

    No Known Activations