INDEX

Explanations

words and phrases indicating position, particularly at the top of lists or ranks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

حوالہ

-0.58

upan

-0.57

至于

-0.56

ERSON

-0.52

ablanca

-0.51

liday

-0.47

 einzu

-0.47

triangleq

-0.46

dû

-0.46

oons

-0.46

POSITIVE LOGITS

PerformLayout

0.94

:✨

0.73

SourceChecksum

0.70

Демографія

0.69

 itſelf

0.69

 bottom

0.68

 '\\;'

0.67

ViewImports

0.66

 zvuky

0.65

 loob

0.65

Activations Density 0.184%

words and phrases indicating position, particularly at the top of lists or ranks

No Comments

No Known Activations