INDEX

Explanations

occurrences of the word "is" and variations of "s"

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

الدراسه

-0.61

 omnes

-0.56

Bhd

-0.55

جوايز

-0.54

apore

-0.53

ῷ

-0.52

 ใหม่

-0.52

 Horne

-0.52

깥

-0.51

 habet

-0.51

POSITIVE LOGITS

Thats

1.00

 Thats

0.99

thats

0.91

 thats

0.84

 שוליים

0.84

 That

0.74

ValueGeneration

0.74

 مشين

0.73

why

0.70

="@+

0.69

Activations Density 0.089%

occurrences of the word "is" and variations of "s"

No Comments

No Known Activations