INDEX

Explanations

bullet points or list items in text

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

Followed by "Q" or special characters

np_acts-logits-general · gemini-2.0-flash

Q: questions

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

OfBirth

-0.65

bootstrapcdn

-0.61

İstinadlar

-0.60

ning

-0.57

Manbalar

-0.56

Weblinks

-0.56

buz

-0.56

Bronnen

-0.56

ings

-0.54

<s>

-0.54

POSITIVE LOGITS

••

1.51

••••

1.29

•••

1.15

.•

1.09

~•

0.98

°•

0.94

er

0.88

 ••

0.87

•

0.84

︎

0.81

Activations Density 0.054%

bullet points or list items in text

Followed by "Q" or special characters

Q: questions

No Comments

No Known Activations