INDEX

Explanations

phrases related to actions and future events

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

httphttps

-0.89

Personendaten

-0.78

 فريبيس

-0.74

BeginContext

-0.72

fromnode

-0.70

Datuak

-0.70

 distanciation

-0.70



-0.69

RenderAtEndOf

-0.69

 tartalomajánló

-0.68

POSITIVE LOGITS

 tentu

0.60

няка

0.57

 Indian

0.53

 probably

0.53

 doubtless

0.52

 likely

0.50

 pretty

0.49

 natuurlijk

0.49

累了

0.47

 chắc

0.46

Activations Density 0.285%

phrases related to actions and future events

No Comments

No Known Activations