Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 12641
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations, especially regions like West, South, East, and North

    oai_token-act-pair · gpt-3.5-turbo

    geographic references to specific regions, particularly those related to the West and South

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.97
    govtrack
    -0.77
    ãĥīãĥ©
    -0.77
    Prof
    -0.76
    BuyableInstoreAndOnline
    -0.76
    ãĤ¢ãĥ«
    -0.71
    PLIC
    -0.70
    facts
    -0.67
    andre
    -0.66
    holders
    -0.65
    POSITIVE LOGITS
     coast
    0.98
     Coast
    0.92
     Midlands
    0.87
     hemisphere
    0.86
     Indies
    0.85
     Territories
    0.83
    isphere
    0.83
     Atlantic
    0.82
     Side
    0.81
     periphery
    0.78
    Activations Density 0.080%

    No Known Activations