INDEX

Explanations

instances of the word "is" in various contexts

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

Precedes "a" or "is"

np_acts-logits-general · gemini-2.0-flash

is followed by a descriptor

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

 Forumite

-0.87

Referències

-0.87

 للاسماء

-0.84

extAlignment

-0.84

featureID

-0.83

 WebDriverWait

-0.82

RectangleBorder

-0.82

 nakalista

-0.78

 rağmen

-0.77

 Administrativna

-0.76

POSITIVE LOGITS

0.65

an

0.63

 coming

0.55

my

0.53

the

0.53

<bos>

0.52

 such

0.51

</blockquote>

0.49

een

0.47

Coming

0.45

Activations Density 0.554%

instances of the word "is" in various contexts

Precedes "a" or "is"

is followed by a descriptor

No Comments

No Known Activations