INDEX

Explanations

copyright and licensing information

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

Copyright notices

np_acts-logits-general · gemini-2.0-flash

copyright followed by all

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

 soon

-0.52

 indeed

-0.48

 &___

-0.47

 inevitably

-0.44

 recently

-0.43

 also

-0.43

 surely

-0.43

غال

-0.41

formik

-0.41

 ASAP

-0.41

POSITIVE LOGITS

StoryboardSegue

0.76

All

0.75

MessageTagHelper

0.71

All

0.63

ALL

0.61

SharedCtor

0.61

all

0.60

يكب

0.58

OGND

0.58

forName

0.57

Activations Density 0.178%

copyright and licensing information

Copyright notices

copyright followed by all

No Comments

No Known Activations