INDEX

Explanations

instances of discrimination based on various characteristics, such as race, gender, or pregnancy

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

quelize

-0.59

/*

-0.56

aspectj

-0.51

JNIEnv

-0.47

 asemenea

-0.47

arrol

-0.46

UnifiedTopology

-0.44

makedirs

-0.44

 складу

-0.44

utory

-0.44

POSITIVE LOGITS

 تضيفلها

0.68

MigrationBuilder

0.65

 beginnetje

0.62

بوابة

0.62

AndEndTag

0.61

LookAnd

0.60

 isComment

0.60

 EconPapers

0.59

IsContent

0.59

 disambiguazione

0.57

Activations Density 0.345%

instances of discrimination based on various characteristics, such as race, gender, or pregnancy

No Comments

No Known Activations