INDEX

Explanations

phrases that indicate comparison and differences between items or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

وط

-0.54

vart

-0.50

ubu

-0.45

unya

-0.45

bren

-0.44

سم

-0.44

 Toute

-0.44

 Shee

-0.43

var

-0.43

hadiran

-0.43

POSITIVE LOGITS

principalColumn

0.79

WebVitals

0.79

IsMutable

0.78

 kasarigan

0.78

ьаж

0.76

UnsafeEnabled

0.69

NameInMap

0.67

 EconPapers

0.67

AnimationsModule

0.65

contentLoaded

0.62

Activations Density 0.640%

phrases that indicate comparison and differences between items or conditions

No Comments

No Known Activations