INDEX

Explanations

words and phrases related to assigning blame

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

alt

-0.57

Alt

-0.56

State

-0.55

enumi

-0.55

lader

-0.55

 ricar

-0.52

الثة

-0.52

 Brice

-0.51

 Unger

-0.50

groupby

-0.49

POSITIVE LOGITS

endphp

0.90

✨:

0.85

 "..\..\..\

0.84

})`

0.84

 JpaRepository

0.83

WebElementEntity

0.82

expandindo

0.81

featureID

0.80

 onCreateView

0.79

+#+#

0.79

Activations Density 0.075%

words and phrases related to assigning blame

No Comments

No Known Activations