INDEX

Explanations

phrases related to examination procedures and requirements

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

Followed by a number or symbol

np_acts-logits-general · gemini-2.0-flash

fixed interest

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

«

-0.52

òi

-0.49

(«

-0.47

wym

-0.43

 practically

-0.41

 auto

-0.40

 pitched

-0.39

 Practically

-0.39

情

-0.38

POSITIVE LOGITS

ſelf

0.88

 Majefty

0.88

 fubject

0.87

 purpoſe

0.86

EndInit

0.84

 propOrder

0.83

OGND

0.82

 esternos

0.82

 ſche

0.81

 Jefus

0.81

Activations Density 0.044%

phrases related to examination procedures and requirements

Followed by a number or symbol

fixed interest

No Comments

No Known Activations