INDEX

Explanations

instances of the word "before" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ſelf

-0.83

KommentareTeilen

-0.81

 Jefus

-0.78

Efq

-0.74

ษัท

-0.73

bolista

-0.72

 følge

-0.71

 habet

-0.68

 Cæsar

-0.68

genstein

-0.68

POSITIVE LOGITS

 before

1.48

before

1.45

BEFORE

1.41

 Before

1.40

 BEFORE

1.35

Before

1.31

 innan

1.09

 sebelum

1.06

 befo

1.03

 før

0.94

Activations Density 0.100%

instances of the word "before" in various contexts

No Comments

No Known Activations