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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 64
    Prev
    Next
    INDEX
    Explanations

    references to a specific place, Arlington, with various contexts such as events, people, and locations within or related to Arlington

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location Arlington

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

    the proper noun "Arlington"

    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
    ggle
    -0.75
    ugal
    -0.74
    oly
    -0.74
    orders
    -0.70
    unal
    -0.70
    unin
    -0.70
    ffer
    -0.68
    occ
    -0.67
    title
    -0.65
    odor
    -0.64
    POSITIVE LOGITS
     Arlington
    1.21
     Heights
    1.16
     Cemetery
    0.91
    INGTON
    0.90
    lington
    0.84
    halla
    0.80
     Bridge
    0.76
     Plaza
    0.76
    dale
    0.75
    itect
    0.74
    Activations Density 0.013%

    No Known Activations