INDEX

Explanations

phrases related to refusal or non-compliance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ammans

-0.50

$_"

-0.47

 Réponses

-0.46

 beſch

-0.45

 Towers

-0.45

 vooz

-0.44

edicated

-0.44

FieldDescriptor

-0.43

dike

-0.43

 насељу

-0.43

POSITIVE LOGITS

 refusing

0.43

 reluctantly

0.39

 refused

0.39

 refuses

0.38

 للمعارف

0.38

 AssemblyTitle

0.37

 refusé

0.36

withIdentifier

0.36

 willingly

0.35

willing

0.35

Activations Density 0.464%

phrases related to refusal or non-compliance

No Comments

No Known Activations