© 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. 2-RES-JB
    11. 1752
    Prev
    Next
    INDEX
    Explanations

    specific names and surnames (Krueger and variations thereof)

    oai_token-act-pair · gpt-3.5-turbo

    the name "Krzanich" and closely related variations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dragonbound
    -0.82
    journal
    -0.76
    Journal
    -0.74
    ORGE
    -0.73
    eering
    -0.70
    BOOK
    -0.68
     quo
    -0.68
    LEASE
    -0.67
     Samoa
    -0.65
     Fairfax
    -0.64
    POSITIVE LOGITS
    usk
    1.12
    ©¶æ¥µ
    1.07
    istani
    1.06
    assic
    1.02
     Kr
    0.95
    asus
    0.93
    uder
    0.92
    ota
    0.91
    atell
    0.90
    anny
    0.89
    Activations Density 0.007%

    No Known Activations