INDEX

Explanations

numeric values, particularly in the context of categories or ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

complexContent

-0.98

 дописавши

-0.77

+#+#

-0.77

ContentAlignment

-0.77

NewUrlParser

-0.73

 Bioaccumulative

-0.73

ItemBackground

-0.70

ValueGeneration

-0.68

 cdti

-0.67

 HasFactory

-0.66

POSITIVE LOGITS

In

0.56

↵↵

0.53

The

0.52

 Tapatalk

0.50

PLICATION

0.50

 Following

0.50

ього

0.49

őle

0.49

Activations Density 0.016%

numeric values, particularly in the context of categories or ratings

No Comments

No Known Activations