INDEX

Explanations

instances of high emphasis or emphasis markers in the text

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

enumi

-0.71

ScopeManager

-0.69

jfree

-0.64

yarnpkg

-0.63

 InputDecoration

-0.63

</caption>

-0.62

HandlerContext

-0.61

 kaynağından

-0.60

migrationBuilder

-0.60

readAs

-0.59

POSITIVE LOGITS

 دیکھیے

0.55

 refusé

0.55

či

0.54

 igång

0.54

 rhestr

0.54

quitous

0.52

HideFlags

0.52

 alemão

0.50

 ‘’

0.50

Activations Density 0.260%

instances of high emphasis or emphasis markers in the text

No Comments

No Known Activations