INDEX

Explanations

events involving conflicts or military actions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

fights

-0.54

 Bombs

-0.52

:✨

-0.51

 للمعارف

-0.50

pushFollow

-0.49

 fights

-0.46

 Fires

-0.45

 linkovi

-0.45

kämp

-0.45

POSITIVE LOGITS

 raid

0.54

 operation

0.53

 coordinated

0.52

 unsuccessful

0.46

 offensive

0.46

 daring

0.46

 attack

0.45

 daylight

0.45

 blitz

0.43

 blit

0.42

Activations Density 0.483%

events involving conflicts or military actions

No Known Activations