INDEX

Explanations

phrases indicating causation or significant implications

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

Follows "of" or "to"

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

__":

-0.51

__':

-0.46

requestCode

-0.42

fromnode

-0.42

Хьажоргаш

-0.42

เอง

-0.41

Française

-0.41

 Kugel

-0.41

zystać

-0.40

()])

-0.39

POSITIVE LOGITS

 faptul

0.98

its

0.94

 lack

0.75

 being

0.72

 adanya

0.70

 Tatsache

0.69

 their

0.69

how

0.66

 fact

0.66

 having

0.65

Activations Density 0.498%

phrases indicating causation or significant implications

Follows "of" or "to"

No Comments

No Known Activations