© 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. 23691
    Prev
    Next
    INDEX
    Explanations

    the word "UR" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "UR"

    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
     Schultz
    -0.74
    olean
    -0.72
     Sands
    -0.72
     Kissinger
    -0.70
    etts
    -0.69
    xon
    -0.68
    makers
    -0.67
     hed
    -0.67
    notes
    -0.65
     Eb
    -0.64
    POSITIVE LOGITS
    UR
    1.10
    POSE
    1.08
    BLE
    1.02
    GER
    0.99
    ARCH
    0.97
    OPE
    0.94
     confir
    0.93
    AGE
    0.93
    pees
    0.92
    DER
    0.91
    Activations Density 0.005%

    No Known Activations