© 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. 3-RES-JB
    11. 3321
    Prev
    Next
    INDEX
    Explanations

    locations or names related to "Gul" or "Kul."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Gul" and its variations, indicating a focus on a specific individual or subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemTracker
    -0.64
     Continued
    -0.63
     WHO
    -0.59
     Hawking
    -0.59
    acters
    -0.59
     Sevent
    -0.59
     Collider
    -0.59
     Pacers
    -0.57
     EDITION
    -0.57
    alth
    -0.57
    POSITIVE LOGITS
    mud
    0.94
    ulp
    0.93
     Gul
    0.88
    pin
    0.85
    gur
    0.84
    zar
    0.84
    indal
    0.83
    mbuds
    0.82
    entle
    0.81
    ongs
    0.81
    Activations Density 0.005%

    No Known Activations