INDEX

Explanations

comparative phrases and terms within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 purpoſe

-1.21

 ſeveral

-1.18

 pleaſure

-1.12

 myſelf

-1.12

 Majefty

-1.12

 ſtate

-1.06

 fubject

-1.02

 Monfieur

-0.96

 Jefus

-0.95

MLLoader

-0.93

POSITIVE LOGITS

 than

1.01

 daripada

0.84

than

0.80

 THAN

0.73

 dibanding

0.69

 rispetto

0.69

 compared

0.69

 niż

0.66

Compared

0.65

 dibandingkan

0.65

Activations Density 0.227%

comparative phrases and terms within the text

No Comments

No Known Activations