INDEX

Explanations

phrases indicating frustration with processes and experiences

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

after "and"

np_acts-logits-general · gemini-2.0-flash

and he, and have

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

tagHelperRunner

-1.05

SharedDtor

-0.91

 tartalomajánló

-0.90

 calendriers

-0.78

yntaxException

-0.74

IUrlHelper

-0.74

ThroughAttribute

-0.73

EndInit

-0.70

StoryboardSegue

-0.68

 Paglinawan

-0.68

POSITIVE LOGITS

 receive

1.69

 receives

1.52

 receiving

1.48

 received

1.38

receive

1.38

 Receive

1.37

Receive

1.28

receiving

1.23

 recieve

1.22

 Receiving

1.21

Activations Density 0.550%

phrases indicating frustration with processes and experiences

after "and"

and he, and have

No Comments

No Known Activations