INDEX

Explanations

references to television channels and their various attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 CreateTagHelper

-0.61

expandindo

-0.58



-0.57

OpenHelper

-0.57

 tartalomajánló

-0.54

NameInMap

-0.54

msgTypes

-0.53

 >=",

-0.53

una

-0.52

MigrationBuilder

-0.51

POSITIVE LOGITS

 channel

0.90

tagHelper

0.81

 channels

0.80

 Channel

0.76

 CHANNEL

0.75

channel

0.75

 Channels

0.73

Channel

0.71

gaz

0.67

 Gazette

0.66

Activations Density 2.358%

references to television channels and their various attributes

No Comments

No Known Activations