© 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. 0-RES-JB
    6. 5193
    Prev
    Next
    INDEX
    Explanations

    references related to New York City

    oai_token-act-pair · gpt-3.5-turbo

    references to New York and its related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conquer
    -0.72
     pause
    -0.68
     horns
    -0.65
     uncertainties
    -0.65
     absorption
    -0.64
     vegetation
    -0.63
     absor
    -0.63
     restricted
    -0.63
     dictator
    -0.62
     clans
    -0.61
    POSITIVE LOGITS
    NY
    4.29
     NY
    2.00
     NYC
    1.96
    ny
    1.95
    NJ
    1.80
     NYPD
    1.54
    NH
    1.44
     NYT
    1.43
    Brook
    1.41
    hattan
    1.40
    Activations Density 0.010%

    No Known Activations