INDEX

Explanations

phrases indicating negotiation or conflict resolution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Monfieur

-0.69

 myſelf

-0.55

 ſeveral

-0.53

hdashline

-0.51

imetry

-0.51

pture

-0.47

 hasattr

-0.47

paigns

-0.47

"{}

-0.47

 theſe

-0.47

POSITIVE LOGITS

httphttps

0.70

too

0.58

WithIOException

0.58

findpost

0.57

 мәкал

0.56

StoryboardSegue

0.55

EndTag

0.55

 тоже

0.54

setupUi

0.54

 ebenfalls

0.54

Activations Density 0.655%

phrases indicating negotiation or conflict resolution

No Comments

No Known Activations