INDEX

Explanations

instances of the word "though"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 للاسماء

-0.82

AutoScale

-0.77

UnitTesting

-0.73

 Kirke

-0.71

 UIFont

-0.69

DATABASES

-0.66

&_

-0.66

ftagPool

-0.65

).[

-0.65

---+

-0.65

POSITIVE LOGITS

 however

0.66

 though

0.63

erdings

0.59

}{*}{}

0.56

 meanwhile

0.56

however

0.54

 entanto

0.53

AndView

0.53

PhysRevD

0.52

 nonetheless

0.52

Activations Density 0.133%

instances of the word "though"

No Comments

No Known Activations