© 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. 7-RES-JB
    11. 12381
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, particularly focusing on the city of New York City

    oai_token-act-pair · gpt-3.5-turbo

    references to New York City

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rar
    -0.94
    ibilities
    -0.78
    wcsstore
    -0.78
    ãĥĦ
    -0.78
    Wan
    -0.75
    gotten
    -0.75
    terness
    -0.74
    riv
    -0.73
    igham
    -0.72
    etsk
    -0.72
    POSITIVE LOGITS
     landmarks
    0.93
     skyline
    0.92
     Council
    0.91
     borough
    0.91
    scape
    0.89
     Orchestra
    0.87
     subway
    0.85
     metropolitan
    0.85
     Mayor
    0.83
     streets
    0.81
    Activations Density 0.033%

    No Known Activations