INDEX

Explanations

expressions related to enjoyment and pleasure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ine

-0.65

netinet

-0.64

ggf

-0.63

 Dalton

-0.61

googleapis

-0.58

Al

-0.57

 Mose

-0.57

 saith

-0.57

-0.56

Dalton

-0.56

POSITIVE LOGITS

enjoy

1.20

 enjoyment

1.16

 enjoy

1.07

 pleaſure

1.06

 Enjoy

1.06

joys

1.05

 enjoyed

1.04

 ENJOY

1.02

Enjoyed

1.01

 itſelf

0.96

Activations Density 0.042%

expressions related to enjoyment and pleasure

No Comments

No Known Activations