INDEX

Explanations

occurrences of the prefix "re-" in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 Theſe

-1.28

 ་་

-1.12

 ainfi

-1.10

 itſelf

-1.07

 Monfieur

-1.05

 ―――――

-1.03

 myſelf

-0.95

 Beſ

-0.93

 ſeveral

-0.93

 Chriſt

-0.92

POSITIVE LOGITS

Re

1.17

re

1.17

Re

1.09

pre

1.03

0.99

0.98

0.93

0.92

Activations Density 0.149%

occurrences of the prefix "re-" in words

No Comments

No Known Activations