INDEX

Explanations

discussions of consequences and repercussions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 tartalomajánló

-0.65

omock

-0.63

 ویکی‌پدیا

-0.57

 Есть

-0.55

seling

-0.55

AddRef

-0.52

 protoimpl

-0.52

zeln

-0.51

hebt

-0.51

 InputDecoration

-0.49

POSITIVE LOGITS

 consequences

1.56

 consequence

1.38

Consequences

1.33

 Consequences

1.33

 repercussions

1.22

 conseguenze

1.20

 conséquences

1.19

 consecuencias

1.15

effects

1.14

 effects

1.11

Activations Density 0.363%

discussions of consequences and repercussions in various contexts

No Comments

No Known Activations