© 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. 6-RES-JB
    11. 2945
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of the location "Brooklyn" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to Brooklyn and its related entities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ional
    -0.94
    OPLE
    -0.81
    orter
    -0.80
    ivia
    -0.79
    inen
    -0.78
    aved
    -0.77
    umar
    -0.77
    oler
    -0.76
    vana
    -0.75
    veh
    -0.74
    POSITIVE LOGITS
     Nets
    1.10
     Borough
    1.04
     Heights
    0.96
     borough
    0.94
    ites
    0.90
     Bridge
    0.90
     Brooklyn
    0.84
    town
    0.78
     Queens
    0.77
     Island
    0.76
    Activations Density 0.020%

    No Known Activations