INDEX

Explanations

expressions related to personal anecdotes and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 ourselves

-0.70

we

-0.67

our

-0.63

 우리

-0.56

我們

-0.56

 chúng

-0.52

 natin

-0.50

我们

-0.49

เรา

-0.49

We

-0.47

POSITIVE LOGITS

 himself

0.83

himself

0.81

 propOrder

0.78

his

0.72

 herself

0.66

 himſelf

0.63

0.62

 kanyang

0.60

herself

0.59

他的

0.57

Activations Density 0.648%

expressions related to personal anecdotes and experiences

No Comments

No Known Activations