INDEX

Explanations

textual references to official communication or documentation

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

 Савезне

-0.87

 للاسماء

-0.82

 <=",

-0.82

 contextLoads

-0.81

 مشين

-0.80

 мәкал

-0.80

Chham

-0.77

Przypisy

-0.77

تقاوى

-0.77

dafx

-0.76

POSITIVE LOGITS

1.05

«

0.83

And

0.81

And

0.78

»

0.77

In

0.76

The

0.76

0.74

In

0.73

↵↵

0.73

Activations Density 0.039%

textual references to official communication or documentation

No Comments

No Known Activations