INDEX

Explanations

negative descriptors associated with health and vitality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

TagMode

-0.81

 وتسجيلات

-0.72

Personensuche

-0.65

 fallu

-0.64

ścic

-0.62

CDCl

-0.60

insics

-0.58

 ویکی‌آمباردا

-0.56

Referanser

-0.56

StreetMap

-0.56

POSITIVE LOGITS

 efficient

0.71

 difficult

0.69

 cool

0.68

 accurate

0.67

 expensive

0.66

 impressive

0.64

 profitable

0.64

 awesome

0.64

 comfortable

0.64

 powerful

0.63

Activations Density 0.457%

negative descriptors associated with health and vitality

No Comments

No Known Activations