© 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. 10-RES-JB
    11. 10601
    Prev
    Next
    INDEX
    Explanations

    phrases related to the location "Manhattan."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Manhattan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orders
    -0.78
    rar
    -0.76
    rations
    -0.76
    rum
    -0.73
    akening
    -0.73
    ebook
    -0.71
    ivia
    -0.70
    ivals
    -0.70
    books
    -0.70
    np
    -0.69
    POSITIVE LOGITS
     Beach
    1.25
     Borough
    1.23
     borough
    1.19
     skyline
    1.06
     skysc
    1.03
     Manhattan
    0.93
     apartment
    0.93
    hattan
    0.92
     City
    0.91
     Harbor
    0.91
    Activations Density 0.036%

    No Known Activations