INDEX

Explanations

conversations around unresolved situations or inquiries

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

Japanese text context

np_acts-logits-general · gemini-2.0-flash

subject marker は

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

-0.49

-0.47

を

-0.46

 के

-0.44

-0.43

への

-0.43

-0.42

に着

-0.42

的其他

-0.42

POSITIVE LOGITS

 CreateTagHelper

1.18

 mergeFrom

1.10

 ExecuteAsync

1.09

 AssemblyTitle

1.02

__":

1.01

featureID

1.01

 itſelf

1.01

interopRequire

1.01

 propOrder

1.00

 myſelf

0.99

Activations Density 0.147%

conversations around unresolved situations or inquiries

Japanese text context

subject marker は

No Comments

No Known Activations