INDEX

Explanations

references to hypocrisy and double standards

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

hypocritical / hypocrite

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 propOrder

-0.47

uaikan

-0.46

angdong

-0.44

arangay

-0.43

 gynhyrchwyd

-0.42

providedIn

-0.41

domada

-0.41

+#+#

-0.41

rinfo

-0.40

codehaus

-0.40

POSITIVE LOGITS

 hypocrisy

0.60

 '\\;'

0.55

 hypocritical

0.54

 hypocrite

0.49

TargetException

0.48

crisy

0.44

hypo

0.43

 ModelExpression

0.43

CppCodeGen

0.41

 precept

0.39

Activations Density 0.217%

references to hypocrisy and double standards

hypocritical / hypocrite

No Comments

No Known Activations

references to hypocrisy and double standards

hypocritical / hypocrite

No Comments

No Known Activations