INDEX

Explanations

patterns and structures related to regular expressions and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 виправивши

-0.92

RenderAtEndOf

-0.86

 onAnimation

-0.83

LEncoder

-0.80

 <<<<<<<<<<<<<<

-0.78

ReusableCell

-0.76

])),

-0.76

NSIndexPath

-0.76

μφωνα

-0.75

LookAnd

-0.73

POSITIVE LOGITS

...

0.59

</em>

0.49

0.48

…

0.48

Hau

0.47

 руб

0.46

bes

0.46

上

0.46

it

0.45

»

0.45

Activations Density 0.277%

patterns and structures related to regular expressions and their components

No Comments

No Known Activations