INDEX

Explanations

phrases and words related to implications and hints within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 Jefus

-0.81

 ویکی‌پدیای

-0.73

 himſelf

-0.72

didSet

-0.70

 дописавши

-0.69

 Majefty

-0.68

ыгана

-0.67

__(/*!

-0.66

]='\

-0.66

ellido

-0.66

POSITIVE LOGITS

 hints

1.03

 hinting

1.00

 hinted

0.95

 hint

0.93

 insinu

0.79

hint

0.78

暗示

0.75

 allude

0.74

 alludes

0.74

Hints

0.71

Activations Density 0.381%

phrases and words related to implications and hints within a context

No Comments

No Known Activations