INDEX

Explanations

mezzo-foreign terms or phrases within 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 @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 esternos

-0.69

UnsafeEnabled

-0.66

ImageContext

-0.65

wixt

-0.59

 nemlig

-0.58

 Walkover

-0.58

__':

-0.55

__":

-0.55

^*)

-0.55

]){

-0.53

POSITIVE LOGITS

processable

0.63

mtrl

0.57

LayoutStyle

0.52

 IActionResult

0.52

 OBITUARY

0.51

########.

0.49

ulemon

0.49

operable

0.47

NYSE

0.47

 doubl

0.47

Activations Density 0.223%

mezzo-foreign terms or phrases within the text

No Comments

No Known Activations