INDEX

Explanations

references to arrows or directional indicators

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

 particulares

-0.75

()?;

-0.74

깐

-0.74

'}

-0.73

contentLoaded

-0.73

 referenties

-0.71

ΗΣ

-0.71

 NUnit

-0.71

#+#

-0.71

BEST

-0.68

POSITIVE LOGITS

 Arrow

1.81

 arrows

1.78

 arrow

1.72

Arrow

1.68

 Arrows

1.67

 ARROW

1.57

Arrows

1.55

ARROW

1.43

arrows

1.43

arrow

1.33

Activations Density 0.129%

references to arrows or directional indicators

No Comments

No Known Activations