INDEX

Explanations

terms related to medical studies and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

↵↵

-0.64

-0.61

 localObject

-0.58

WebpackPlugin

-0.56

تفصیلات

-0.48

schod

-0.48

izophrenia

-0.48

 assolu

-0.47

 embolism

-0.47

yelidikan

-0.46

POSITIVE LOGITS

CppMethod

0.73

الحياه

0.69

sizeCache

0.69

()];

0.67

 ModelExpression

0.66

TypedDataSet

0.66

invokeLater

0.65

](#

0.65

`,

0.64

 Pristupljeno

0.61

Activations Density 1.703%

terms related to medical studies and measurements

No Comments

No Known Activations