INDEX

Explanations

words and phrases related to causality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Geplaatst

-0.80

 للمعارف

-0.77

 AssemblyCompany

-0.75

posedge

-0.74

tonode

-0.73

 itſelf

-0.72

ScopeManager

-0.71

Personendaten

-0.67

 Wikimedijinoj

-0.67

انيف

-0.66

POSITIVE LOGITS

ca

0.62

Ca

0.61

Ca

0.53

Captor

0.45

ca

0.44

usual

0.41

dr

0.41

 تص

0.41

BIG

0.40

berkeley

0.38

Activations Density 0.086%

words and phrases related to causality

No Comments

No Known Activations