INDEX

Explanations

words related to physical locations or positioning in space

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pitié

-0.76

lccn

-0.72

épaisseur

-0.66

 avoient

-0.65

 prochains

-0.64

 sesta

-0.63

 prochaines

-0.63

avorite

-0.62

iotti

-0.61

]`

-0.61

POSITIVE LOGITS

ArgsConstructor

0.71

IntoConstraints

0.70

PreferredItem

0.65

 kasarigan

0.64

 оригіналу

0.64

 OFDb

0.63

HostException

0.61

audiovisuel

0.61

 pinulongan

0.58

 للمعارف

0.58

Activations Density 0.329%

words related to physical locations or positioning in space

No Comments

No Known Activations