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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4216
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "NJ" (New Jersey)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical locations, specifically New Jersey

    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
     Urug
    -0.82
     Gy
    -0.82
     Salvador
    -0.77
     Rica
    -0.75
     Dele
    -0.74
     Ragnar
    -0.71
     Bolivia
    -0.71
    ####
    -0.70
     Gn
    -0.70
     Franç
    -0.69
    POSITIVE LOGITS
     NJ
    3.04
    NJ
    2.86
    nc
    1.61
     Newark
    1.39
    NH
    1.37
     Rutgers
    1.32
     NH
    1.28
     Camden
    1.23
    aucus
    1.16
    onte
    1.12
    Activations Density 0.031%

    No Known Activations