INDEX

Explanations

phrases indicating appreciation or evoking curiosity about potential outcomes

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

when

-0.61

When

-0.55

-0.52

-0.51

-0.49

FROM

-0.48

-0.47

would

-0.47

Even

-0.46

POSITIVE LOGITS

 مرئيه

1.05

InjectAttribute

1.05

 للاسماء

1.00

存于互联网档案馆

0.96

 تانيه

0.93

 ویکی‌پدی

0.93

 виправивши

0.92

ThroughAttribute

0.92

 ISTAT

0.90

 Normdatei

0.89

Activations Density 0.207%

phrases indicating appreciation or evoking curiosity about potential outcomes

No Comments

No Known Activations