INDEX

Explanations

positive adjectives describing quality or value

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

exitRule

-0.56

 cardíaca

-0.53

 aveug

-0.51

UserScript

-0.50

hidupan

-0.50

 mariée

-0.48

 paroi

-0.48

RenderAtEndOf

-0.47

 hereof

-0.47

vark

-0.47

POSITIVE LOGITS

 ILogger

0.63

#+#

0.58

 versatile

0.57

 versatility

0.56

 affordable

0.55

 MessageBoxIcon

0.55

 AssemblyCulture

0.55

 maneuver

0.53

ZAP

0.52

 adaptable

0.52

Activations Density 0.102%

positive adjectives describing quality or value

No Comments

No Known Activations