INDEX

Explanations

specific patterns in structured data or code, particularly focusing on elements such as delimiters and identifiers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

queryInterface

-0.85

 snippetHide

-0.75

enderror

-0.74

 <>",

-0.72

+#+#

-0.72

 bezeichneter

-0.70

richTextPanel

-0.67

 FetchType

-0.67

 rospy

-0.67

endphp

-0.66

POSITIVE LOGITS

cor

0.44

 всю

0.43

Portály

0.42

pled

0.41

menos

0.41

kos

0.41

chism

0.41

èdia

0.41

HS

0.41

فس

0.40

Activations Density 0.597%

specific patterns in structured data or code, particularly focusing on elements such as delimiters and identifiers

No Comments

No Known Activations