INDEX

Explanations

sections labeled with academic or formal titles, especially those marked by specific codes or reference points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 multiple

-0.69

 each

-0.69

 typically

-0.68

new

-0.65

 back

-0.64

 lots

-0.64

 higher

-0.63

 primarily

-0.62

 using

-0.62

 only

-0.61

POSITIVE LOGITS

sizeCache

0.93

WillAppear

0.92

<bos>

0.90

PositiveButton

0.90

InjectAttribute

0.89

 nakalista

0.89

 дописавши

0.88

RectangleBorder

0.88

msgTypes

0.80

出版年

0.79

Activations Density 0.180%

sections labeled with academic or formal titles, especially those marked by specific codes or reference points

No Comments

No Known Activations