INDEX

Explanations

quotation marks and dialogue indicators in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AndEndTag

-1.04

pozdrawiam

-0.94

$_"

-0.93

 Houſe

-0.91

\<^

-0.86

RetentionPolicy

-0.85

 itſelf

-0.84

 houſe

-0.81

>\<^

-0.81

ſelf

-0.80

POSITIVE LOGITS

“

1.35

“

1.22

.“

1.11

”

0.93

。“

0.90

‘

0.90

‘

0.86

：“

0.82

.”

0.79

，“

0.79

Activations Density 0.083%

quotation marks and dialogue indicators in text

No Comments

No Known Activations