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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6339
    Prev
    Next
    INDEX
    Explanations

    mentions of quotas, particularly in the context of gender representation or resource management

    oai_token-act-pair · gpt-3.5-turbo

    references to quotas

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

    No Comments

    Negative Logits
    akening
    -0.70
    gotten
    -0.70
    adden
    -0.66
    azeera
    -0.65
    description
    -0.65
    ument
    -0.64
    paio
    -0.63
     Glory
    -0.63
    turn
    -0.62
    rupt
    -0.62
    POSITIVE LOGITS
     quota
    1.25
     quotas
    1.24
     allocations
    0.78
     tracts
    0.72
     allot
    0.70
     bott
    0.68
     allotted
    0.68
     dispens
    0.65
    pling
    0.63
     allocation
    0.61
    Activations Density 0.011%

    No Known Activations