© 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. 0-RES-JB
    11. 8388
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Blasio, particularly in a political context

    oai_token-act-pair · gpt-3.5-turbo

    references to Mayor Bill de Blasio and related locations or contexts

    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
     Bai
    -0.79
     armour
    -0.78
    ovo
    -0.75
     clans
    -0.75
     Kur
    -0.75
     armoured
    -0.71
     Kab
    -0.69
     detach
    -0.69
    gam
    -0.68
     Disc
    -0.67
    POSITIVE LOGITS
     NYC
    2.84
     Blasio
    2.76
     Bronx
    2.73
     NYPD
    2.52
     Staten
    2.51
     MTA
    2.15
     Cuomo
    2.08
     Giuliani
    2.07
     Brooklyn
    2.07
     Manhattan
    2.03
    Activations Density 0.042%

    No Known Activations