INDEX

Explanations

phrases related to conflict, accusations, and military actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

addPreferredGap

-0.56

acije

-0.54

httphttps

-0.53

classmethod

-0.53

iertas

-0.51

ungkinkan

-0.49

 romantique

-0.49

 useRef

-0.48

abetes

-0.48

ższych

-0.47

POSITIVE LOGITS

 against

0.73

complexContent

0.66

ArrowToggle

0.64

setVerticalGroup

0.60

fjspx

0.60

 против

0.59

//-->

0.58

against

0.56

 gegen

0.56

 opponents

0.55

Activations Density 0.558%

phrases related to conflict, accusations, and military actions

No Comments

No Known Activations