INDEX

Explanations

terms associated with transparency and clarity

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

LinkId

-0.72

msgTypes

-0.72

 ***!

-0.71

لينكات

-0.66

ंदीखरीदारी

-0.65

Enllaces

-0.63

 BIBSYS

-0.63

/**

-0.62

SerializedSize

-0.62

 समीक्षक

-0.61

POSITIVE LOGITS

 transparency

1.06

 transparent

0.95

 Transparency

0.93

transparent

0.91

Transparency

0.91

 transpar

0.89

 Transparent

0.85

transparency

0.84

Transparent

0.81

 disruptions

0.76

Activations Density 0.053%

terms associated with transparency and clarity

No Comments

No Known Activations