INDEX

Explanations

expressions of surprise or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 myſelf

-1.10

 itſelf

-0.98

Efq

-0.95

 useRouter

-0.94

 houſe

-0.89

 themſelves

-0.87

 himſelf

-0.85

 Houſe

-0.85

 ſeveral

-0.78

 againſt

-0.78

POSITIVE LOGITS

Oh

1.19

Oh

1.11

oh

1.00

oh

0.99

OH

0.92

OH

0.83

Ohh

0.81

 sweet

0.78

็จ

0.76

Ohhhh

0.76

Activations Density 0.061%

expressions of surprise or emphasis

No Comments

No Known Activations