INDEX

Explanations

terms related to language or translation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 فريبيس

-0.77

+#+#

-0.74

 صوتيه

-0.69

RenderAtEndOf

-0.67

---*/

-0.64

 utafitiHapana

-0.63

 الحره

-0.63

SBATCH

-0.62

NameInMap

-0.60

FunctionFlags

-0.60

POSITIVE LOGITS

ANG

0.89

 Engl

0.87

Ang

0.86

 Angels

0.85

 Angeli

0.85

Engl

0.85

 angels

0.84

Angels

0.84

 Engels

0.83

Ang

0.82

Activations Density 0.271%

terms related to language or translation

No Comments

No Known Activations