INDEX

Explanations

various patterns of punctuation, particularly commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-1.33

 itſelf

-1.30

 utafitiHapana

-1.21

:✨

-1.21

IVEREF

-1.14

 ―――――

-1.14

 myſelf

-1.13

ItemBackground

-1.13

EDEFAULT

-1.12

 ModelExpression

-1.12

POSITIVE LOGITS

0.93

0.85

↵

0.84

0.77

</td>

0.72

0.71

and

0.64

0.63

、

0.63

0.60

Activations Density 0.244%

various patterns of punctuation, particularly commas

No Comments

No Known Activations