INDEX

Explanations

specific technical terms and variables across different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

⁩

-0.71

енча

-0.68

ammans

-0.64

brium

-0.63

writeFieldEnd

-0.60

 вікі

-0.60

 ["",

-0.59

“...

-0.58

StructEnd

-0.58

IsContent

-0.58

POSITIVE LOGITS

 […]

0.50

XmlAccessType

0.49

wieś

0.47

…

0.47

 recu

0.46

ษา

0.44

–

0.44

LookAnd

0.43

Continue

0.43

لينكات

0.43

Activations Density 0.945%

specific technical terms and variables across different contexts

No Comments

No Known Activations