© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3423
    Prev
    Next
    INDEX
    Explanations

    instances where someone is applying for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to applications or requests for permissions and licenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avid
    -0.76
    heid
    -0.75
    nick
    -0.71
    deen
    -0.71
     vividly
    -0.67
    worn
    -0.67
    ï¸ı
    -0.66
    ilst
    -0.66
    pointer
    -0.65
    night
    -0.64
    POSITIVE LOGITS
     inclusion
    1.11
     exemption
    1.08
     exemptions
    1.06
     waivers
    0.99
     admission
    0.99
     membership
    0.95
     bankruptcy
    0.95
     renewal
    0.94
     permission
    0.93
     citizenship
    0.92
    Activations Density 0.118%

    No Known Activations