INDEX

Explanations

test case development instructions and parameters

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

Followed by "is" or a question

np_acts-logits-general · gemini-2.0-flash

questions asking "Which"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Życiorys

-0.47

Фото

-0.43

ÉM

-0.43

 Cassel

-0.42

Depuis

-0.42

 Benedetto

-0.41

 vVar

-0.40

 уж

-0.40

 colectiva

-0.39

WithMany

-0.39

POSITIVE LOGITS

 nào

0.88

 LEAST

0.86

tagext

0.81

 للاسماء

0.80

 Which

0.79

ftagPool

0.78

下列

0.76

 TRUE

0.74

 CORRECT

0.73

Which

0.72

Activations Density 0.780%

test case development instructions and parameters

Followed by "is" or a question

questions asking "Which"

No Comments

No Known Activations