INDEX

Explanations

contrasting conjunctions and phrases indicating disagreement or qualification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

gtest

-0.51

PostMapping

-0.46

żym

-0.46

➊

-0.45

bitField

-0.45

netbeans

-0.43

 pytest

-0.42

complexType

-0.42

XCTAssert

-0.42

ViewFeatures

-0.41

POSITIVE LOGITS

出版年

0.78

 समीक्षक

0.74

GOTREF

0.74

NameInMap

0.67

ConstraintMaker

0.66

 saites

0.65

 يتيمه

0.65

曖昧さ回避

0.65

InjectAttribute

0.65

Попис

0.64

Activations Density 0.286%

contrasting conjunctions and phrases indicating disagreement or qualification

No Comments

No Known Activations