© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 11338
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location, Arlington, often related to events and news happening there

    oai_token-act-pair · gpt-3.5-turbo

    references to Arlington, particularly Arlington National Cemetery

    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
    ugal
    -0.80
    ggle
    -0.79
    oly
    -0.79
    osexual
    -0.74
    ocide
    -0.74
    ĨĴ
    -0.73
    acca
    -0.71
    nir
    -0.69
    peg
    -0.69
    iatrics
    -0.68
    POSITIVE LOGITS
     Heights
    1.05
    lington
    0.96
    INGTON
    0.94
     Arlington
    0.92
    ingham
    0.83
     Cemetery
    0.83
     Bridge
    0.78
    dale
    0.78
     Reborn
    0.75
     Borough
    0.74
    Activations Density 0.014%

    No Known Activations