INDEX

Explanations

instances of the word "because" indicating causal relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Shand

-0.84

 nadzieję

-0.77

 Lockheed

-0.72

 Kalman

-0.71

 Henk

-0.71

ffilm

-0.70

ſelf

-0.70

olyte

-0.69

meals

-0.68

enneth

-0.68

POSITIVE LOGITS

 because

2.26

Because

2.19

because

2.17

 Because

2.09

 BECAUSE

2.07

 porque

1.84

ECAUSE

1.70

 perché

1.61

porque

1.54

 Porque

1.54

Activations Density 0.099%

instances of the word "because" indicating causal relationships

No Comments

No Known Activations