© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17040
    Prev
    Next
    INDEX
    Explanations

    references to specific neighborhoods in New York City, focusing on the Bronx and Harlem

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations, particularly the Bronx and Harlem

    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
    orthy
    -0.88
    éĸ
    -0.85
    ivia
    -0.84
    inen
    -0.80
    AKING
    -0.77
    neau
    -0.76
    OTT
    -0.74
    æ³
    -0.72
    akers
    -0.71
    ontent
    -0.70
    POSITIVE LOGITS
     Bronx
    1.13
     Zoo
    0.96
     Borough
    0.82
    xual
    0.78
     Awakens
    0.77
     Doodle
    0.72
     Harlem
    0.71
     Gren
    0.70
     Brooklyn
    0.69
     Orchestra
    0.68
    Activations Density 0.012%

    No Known Activations