INDEX

Explanations

negative qualifiers and phrases that express doubt or negation

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

!*\

-0.56

 لينك

-0.52

GetAxis

-0.50

kapet

-0.48

+#+#

-0.47

Parcelize

-0.46

 ellers

-0.46

itzender

-0.44

ventory

-0.44

PerformLayout

-0.44

POSITIVE LOGITS

tagHelperRunner

0.99

 שוליים

0.70

})$}

0.61

BeginContext

0.59

 }}$}

0.58

じゃなくて

0.58

 समीक्षक

0.57

Personendaten

0.56

 Taktlose

0.55

 '\\;'

0.54

Activations Density 0.226%

negative qualifiers and phrases that express doubt or negation

No Comments

No Known Activations