INDEX

Explanations

terms and phrases related to mental frameworks and attitudes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

esgue

-0.55

 étrangère

-0.54

UrlEncoded

-0.53

 للاسماء

-0.50

 Bomb

-0.49

 NoSuch

-0.47

 Савезне

-0.47

urlopen

-0.46

Chham

-0.45

POSITIVE LOGITS

 mindset

1.16

 Mindset

1.06

 mentality

0.89

 attitude

0.70

attitude

0.68

mind

0.61

 attitudes

0.61

Attitude

0.61

titudes

0.60

 actitud

0.60

Activations Density 0.006%

terms and phrases related to mental frameworks and attitudes

No Comments

No Known Activations