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. 11-RES-JB
    6. 3971
    Prev
    Next
    INDEX
    Explanations

    political figures from New York City

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their actions in New York

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ormon
    -0.93
     Malays
    -0.92
     scrut
    -0.92
     Xen
    -0.91
    untu
    -0.86
     ub
    -0.84
     GST
    -0.84
    ubuntu
    -0.81
     Kodi
    -0.81
     Lumpur
    -0.81
    POSITIVE LOGITS
     Bronx
    2.11
     NYPD
    2.09
     Staten
    2.07
     Brooklyn
    2.01
     NYC
    1.98
    NY
    1.93
     Manhattan
    1.86
     Blasio
    1.85
     NY
    1.83
     Queens
    1.81
    Activations Density 0.526%

    No Known Activations