INDEX

Explanations

occurrences and references to specific sections and editors in legal or formal documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

存于互联网档案馆

-0.57

 InputDecoration

-0.51

éphane

-0.44

RTLD

-0.43

Skocz

-0.43

Diwedd

-0.43

OrEmpty

-0.42

UserScript

-0.42

IMPORTED

-0.41

setAccessible

-0.41

POSITIVE LOGITS

wise

0.50

 hinweg

0.47

ीय

0.47

별

0.46

 Leader

0.46

 headings

0.44

ไหน

0.43

 leader

0.43

تقاوى

0.42

省市镇

0.42

Activations Density 0.614%

occurrences and references to specific sections and editors in legal or formal documentation

No Comments

No Known Activations