Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 88
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Uruguay

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "UD" and its related context within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The main thing this neuron does is find instances of the "UD" character sequence

    oai_token-act-pair · gpt-4-turbo
    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
    bell
    -0.71
    strength
    -0.70
    tein
    -0.66
    horn
    -0.64
     fries
    -0.64
     juices
    -0.63
     sear
    -0.62
     plates
    -0.61
     Slaughter
    -0.60
    cold
    -0.59
    POSITIVE LOGITS
    UD
    1.15
    IFIED
    1.10
    PDATE
    0.98
    PLIC
    0.94
    iamond
    0.90
    BLE
    0.89
    geon
    0.84
    ITION
    0.84
    elta
    0.83
    ITY
    0.82
    Activations Density 0.007%

    No Known Activations