© 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. 7-RES-JB
    11. 14589
    Prev
    Next
    INDEX
    Explanations

    target groups or categories of people

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups of people or demographics

    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
     Deadly
    -0.71
    inventoryQuantity
    -0.66
    ILA
    -0.65
    ãģĻ
    -0.64
     Empress
    -0.64
     Humane
    -0.63
    ciation
    -0.63
     Anything
    -0.62
     Corpus
    -0.61
    ahime
    -0.60
    POSITIVE LOGITS
     opted
    0.90
     prefer
    0.87
     succumbed
    0.85
     experimented
    0.82
     surveyed
    0.81
     mistakenly
    0.80
     perished
    0.80
     hesitate
    0.78
     swear
    0.77
     agree
    0.77
    Activations Density 0.252%

    No Known Activations