© 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. 0-RES-JB
    11. 22254
    Prev
    Next
    INDEX
    Explanations

    references to organizations or groups named "Regional."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific regional entities or organizations

    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
     tack
    -0.79
     mant
    -0.70
     exoner
    -0.66
    aus
    -0.66
     beware
    -0.65
     silence
    -0.64
     slippery
    -0.64
     cheaply
    -0.63
     cure
    -0.62
     curing
    -0.62
    POSITIVE LOGITS
     Regional
    3.67
     Region
    2.16
     regional
    1.79
     Provincial
    1.68
     Regions
    1.55
    Region
    1.51
     Municipal
    1.47
     Local
    1.36
     Rural
    1.35
     region
    1.24
    Activations Density 0.015%

    No Known Activations