© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14682
    Prev
    Next
    INDEX
    Explanations

    terms related to specific locations or territories

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "turf" or territory

    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
     Clement
    -0.68
    essential
    -0.68
    nes
    -0.67
    esc
    -0.66
    hing
    -0.66
    Cass
    -0.66
     Hungry
    -0.65
    Anim
    -0.64
    azaki
    -0.64
    aton
    -0.63
    POSITIVE LOGITS
     turf
    4.24
     jurisd
    1.05
     asphalt
    1.03
     clubhouse
    1.01
     lac
    0.98
     pavement
    0.97
     incumb
    0.94
     sideline
    0.94
     lawn
    0.92
     sovere
    0.90
    Activations Density 0.019%

    No Known Activations