INDEX

Explanations

terms related to corruption, particularly within governmental or institutional contexts

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

starting with "Cor" or "Kor"

np_acts-logits-general · gemini-2.0-flash

corrupt, coronal, coralline, corti-

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

########.

-0.68

phrag

-0.58

yntaxException

-0.58

 تضيفلها

-0.56

 Dray

-0.53

pencer

-0.53

findpost

-0.51

panou

-0.50

ADVERTISEMENT

-0.50

 références

-0.50

POSITIVE LOGITS

COR

1.21

cor

1.19

cor

1.15

Cor

1.14

kor

1.12

Cor

1.11

COR

1.06

Kor

1.04

 Corcoran

0.96

KOR

0.93

Activations Density 0.232%

terms related to corruption, particularly within governmental or institutional contexts

starting with "Cor" or "Kor"

corrupt, coronal, coralline, corti-

No Comments

No Known Activations