INDEX

Explanations

elements of conversational dialogue that indicate emotional responses or judgments

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

னர்

-0.51

盾

-0.51

lineno

-0.50

┻

-0.48

}?>

-0.47

 نے

-0.47

 ам

-0.47

}]

-0.47

≦

-0.46

цами

-0.46

POSITIVE LOGITS

出版年

0.77

it

0.72

 ujednoznacz

0.71

DeleteBehavior

0.70

 then

0.69

 ProtoMessage

0.68

الدراسه

0.63

 فريبيس

0.62

 surely

0.62

AndEndTag

0.62

Activations Density 0.339%

elements of conversational dialogue that indicate emotional responses or judgments

No Comments

No Known Activations