© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6876
    Prev
    Next
    INDEX
    Explanations

    locations or places, especially focusing on the borough of Queens

    oai_token-act-pair · gpt-3.5-turbo

    references to the location "Queens."

    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
    rious
    -0.76
    ischer
    -0.73
    shapeshifter
    -0.69
    ËĪ
    -0.67
    eredith
    -0.66
    aneous
    -0.66
    UCK
    -0.66
    akable
    -0.65
    ãĤ·ãĥ£
    -0.65
    angible
    -0.65
    POSITIVE LOGITS
     Queens
    1.14
     Borough
    0.95
    uits
    0.89
     borough
    0.85
    boro
    0.81
    mares
    0.76
    borough
    0.75
    uit
    0.75
    interstitial
    0.74
     alley
    0.73
    Activations Density 0.005%

    No Known Activations