© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20792
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the "South" region

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "South."

    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
     compromise
    -0.63
     codec
    -0.62
     inheritance
    -0.62
     feasibility
    -0.60
    ysis
    -0.58
     misuse
    -0.58
     moot
    -0.58
     trillion
    -0.58
     impart
    -0.58
     calculator
    -0.58
    POSITIVE LOGITS
    western
    1.30
    ampton
    1.23
    west
    1.21
    lake
    1.09
     Shore
    1.09
    vale
    1.08
     Coast
    1.04
    side
    1.04
     Carolina
    1.02
    park
    1.01
    Activations Density 0.057%

    No Known Activations