INDEX

Explanations

instances of the word "go" in various contexts, suggesting it is focused on references to navigation or movement

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

 fras

-0.66

autant

-0.63

 Alte

-0.61

ként

-0.60

DateTimeField

-0.59

ting

-0.58

}}],

-0.58

 أنّ

-0.57

“

-0.57

Utils

-0.56

POSITIVE LOGITS

Go

2.15

go

2.06

Go

2.00

go

1.98

GO

1.92

GO

1.84

 goes

1.26

 Goes

1.23

 goTo

1.20

 Goss

1.18

Activations Density 0.053%

instances of the word "go" in various contexts, suggesting it is focused on references to navigation or movement

No Comments

No Known Activations