INDEX

Explanations

pronouns, particularly focusing on the word "it."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 doubtnut

-0.93

 ſeveral

-0.79

 myſelf

-0.78

 Jefus

-0.77

 Chriftian

-0.76

 Monfieur

-0.75

 itſelf

-0.73

 poffible

-0.73

 aprendido

-0.72

WebServlet

-0.71

POSITIVE LOGITS

 having

0.69

having

0.66

Having

0.62

 Having

0.60

 Have

0.50

 with

0.49

arResult

0.49

Have

0.49

 OMITBAD

0.48

ंदीखरीदारी

0.48

Activations Density 0.218%

pronouns, particularly focusing on the word "it."

No Comments

No Known Activations