© 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. 4-RES-JB
    11. 16290
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, particularly the city of Oxford

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the University of Oxford

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

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.82
    ++++
    -0.75
    ++++++++
    -0.73
    venge
    -0.73
    selage
    -0.72
    SHIP
    -0.72
     quo
    -0.72
    ////////
    -0.70
    Magikarp
    -0.69
    VICE
    -0.69
    POSITIVE LOGITS
    shire
    1.59
     Circus
    1.00
    bridge
    0.93
     Oxford
    0.93
    hurst
    0.91
     University
    0.88
     Manor
    0.84
    ington
    0.83
     comma
    0.81
     Shakespeare
    0.77
    Activations Density 0.007%

    No Known Activations