INDEX

Explanations

formatted section headings or important notations in the text

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

 виправивши

-0.99

rungsseite

-0.89

 contextLoads

-0.84

)";

-0.82

StructEnd

-0.79

 tartalomajánló

-0.79

 bezeichneter

-0.79

Portale

-0.78

 itſelf

-0.76

'},

-0.76

POSITIVE LOGITS

**

0.90

###

0.87

##

0.72

star

0.70

**

0.67

####

0.64

 ***!

0.59

 star

0.59

 reported

0.57

##

0.55

Activations Density 0.367%

formatted section headings or important notations in the text

No Comments

No Known Activations