INDEX

Explanations

phrases related to recommendations and evaluations

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

 nahilalakip

-1.18

setVerticalGroup

-1.06

oredCriteria

-0.96

GEBURTSDATUM

-0.93

 Paglinawan

-0.92

AutoScaleMode

-0.91

 ProtoMessage

-0.90

Personendaten

-0.88

انيف

-0.87

POSITIVE LOGITS

us

0.60

tri

0.50

me

0.49

ताब

0.47

시

0.47

it

0.47

No

0.46

0.45

no

0.45

0.43

Activations Density 0.856%

phrases related to recommendations and evaluations

No Comments

No Known Activations