INDEX

Explanations

instances of the word 'all'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 propOrder

-0.54

 المعيارى

-0.52

 ProtoMessage

-0.52

SpringRunner

-0.50

 للمعارف

-0.50

Autoritní

-0.49

 незавершена

-0.47

MLLoader

-0.47

AnchorTagHelper

-0.46

MigrationBuilder

-0.46

POSITIVE LOGITS

tagHelperRunner

0.60

TagMode

0.58

 fallu

0.40

familiar

0.39

 CGFloat

0.39

 Something

0.39

strptime

0.38

 gleaned

0.38

boldmath

0.36

Something

0.36

Activations Density 0.416%

instances of the word 'all'

No Comments

No Known Activations