INDEX

Explanations

phrases related to legal terms and conditions involving financial institutions and behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 geldig

-0.51

Parti

-0.47

kib

-0.47

typename

-0.47

탤

-0.47

 Briar

-0.47

{~

-0.46

 kaynağından

-0.46

 Numa

-0.46

 sant

-0.46

POSITIVE LOGITS

WriteTagHelper

0.77

 ویکی‌پدی

0.63

Viited

0.56

}$

0.55

 required

0.55

 requisite

0.54

principalColumn

0.51

ungere

0.51

новниш

0.51

 дописавши

0.49

Activations Density 1.151%

phrases related to legal terms and conditions involving financial institutions and behavior

No Comments

No Known Activations