INDEX

Explanations

repetitive usage of the word "I."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-1.29

 ―――――

-1.26

 itſelf

-1.25

 faſt

-1.14

ſelves

-1.14

 ་་

-1.13

 iſt

-1.12

 Monfieur

-1.10

 ſeveral

-1.09

 myſelf

-1.08

POSITIVE LOGITS

it

1.13

1.09

he

1.09

we

1.08

0.84

she

0.84

you

0.83

↵↵

0.79

we

0.78

it

0.77

Activations Density 0.173%

repetitive usage of the word "I."

No Comments

No Known Activations