INDEX

Explanations

mathematical symbols and terms related to legal or formal documents

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

☆☆☆☆

-0.58

ISTR

-0.48

wur

-0.43

kopp

-0.42

 hydropon

-0.42

Dit

-0.41

verläs

-0.41

luk

-0.41

ịp

-0.41

Kens

-0.40

POSITIVE LOGITS

↵

1.17

',...

1.07

0.94

 […]

0.92

IntoConstraints

0.91

...')

0.88

 ivelany

0.87

 parseFrom

0.87

'],

0.84

0.83

Activations Density 3.453%

mathematical symbols and terms related to legal or formal documents

No Comments

No Known Activations