INDEX

Explanations

comparative phrases that highlight similarities or consistencies across different subjects or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 gainera

-0.71

……"

-0.65

citep

-0.62

mybatisplus

-0.59

}></

-0.59

HtmlAttribute

-0.59

Efq

-0.59

omości

-0.58

hicle

-0.58

-0.57

POSITIVE LOGITS

 disambiguazione

0.63

Geplaatst

0.59

клопе

0.57

dataclass

0.55

'{@

0.54

fromCharCode

0.53

UnsafeEnabled

0.49

AndEndTag

0.44

 gọi

0.43

ждают

0.43

Activations Density 0.432%

comparative phrases that highlight similarities or consistencies across different subjects or contexts

No Comments

No Known Activations