Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 8720
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the NYPD (New York Police Department)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the NYPD and its activities or associated entities

    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
    pring
    -1.07
    held
    -0.91
    wagen
    -0.87
    fully
    -0.82
    vo
    -0.80
    heid
    -0.80
    ioned
    -0.79
    utm
    -0.77
    fee
    -0.77
    owing
    -0.77
    POSITIVE LOGITS
     NYPD
    0.95
     Borough
    0.87
    ©¶æ
    0.80
     Brut
    0.79
     orchestra
    0.75
     borough
    0.75
     Nets
    0.74
     brass
    0.74
     Unleashed
    0.74
     Orchestra
    0.74
    Activations Density 0.007%

    No Known Activations