INDEX

Explanations

pronouns and demonstrative articles

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

 Houſe

-0.96

wiſe

-0.90

 Савезне

-0.88

 houſe

-0.88

Controllo

-0.87

 Anſ

-0.84

 ―――――

-0.84

 myſelf

-0.83

 pleaſure

-0.82

 Reſ

-0.81

POSITIVE LOGITS

he

0.96

He

0.95

It

0.93

it

0.87

 They

0.85

he

0.84

Det

0.83

Det

0.80

 they

0.80

He

0.76

Activations Density 0.038%

pronouns and demonstrative articles

No Comments

No Known Activations