INDEX

Explanations

phrases related to justifications or reasons for actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

JNIEnv

-0.74

Efq

-0.73

 nostru

-0.73

 hvil

-0.72

 Monfieur

-0.70

 ljus

-0.69

//}

-0.67

 eorum

-0.67

 Theſe

-0.67

 zelve

-0.66

POSITIVE LOGITS

 because

0.69

 sake

0.63

Rüyada

0.62

 Because

0.61

Because

0.60

because

0.58

GEBURTSDATUM

0.56

 weil

0.56

ůli

0.55

 BECAUSE

0.55

Activations Density 0.141%

phrases related to justifications or reasons for actions

No Comments

No Known Activations