© 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. 1-RES-JB
    11. 10453
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a person named "Hajdu"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Haj" and its various mentions in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ________________
    -0.74
     Newton
    -0.67
     Rhodes
    -0.65
     magnification
    -0.65
     Cosponsors
    -0.65
     Proced
    -0.64
    ACTED
    -0.64
     Gemini
    -0.64
     Commonwealth
    -0.63
    Social
    -0.62
    POSITIVE LOGITS
     Haj
    1.16
     pilgrims
    1.00
     pilgrimage
    0.96
    riks
    0.91
    azard
    0.90
    ih
    0.87
    isoft
    0.85
    aji
    0.84
    quet
    0.83
    renheit
    0.82
    Activations Density 0.009%

    No Known Activations