© 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. 2-RES-JB
    11. 8973
    Prev
    Next
    INDEX
    Explanations

    references to the city of New York

    oai_token-act-pair · gpt-3.5-turbo

    mentions of New York

    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
    âķIJâķIJ
    -0.78
    TPP
    -0.78
     stewards
    -0.76
    VPN
    -0.74
    unct
    -0.71
    EMP
    -0.69
    kick
    -0.69
    vol
    -0.69
    held
    -0.65
    selection
    -0.65
    POSITIVE LOGITS
     City
    1.10
     Mellon
    1.03
     York
    0.84
    town
    0.83
     Knicks
    0.82
     Harbor
    0.81
     Yankees
    0.81
     Giants
    0.80
     Cosmos
    0.80
     Times
    0.78
    Activations Density 0.031%

    No Known Activations