INDEX

Explanations

concepts related to discrepancies or disagreements in studies or reports

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

preceding a problem or situation

np_acts-logits-general · gemini-2.0-flash

problem or emergence

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

AndEndTag

-0.56

zeczytaj

-0.51

 onAnimation

-0.50

 kullanılan

-0.49

 ندارد

-0.48

 Schwal

-0.47

PostExecute

-0.46

InstanceState

-0.46

 beispiel

-0.45

 riuscito

-0.45

POSITIVE LOGITS

 emerge

2.06

 emerged

1.99

 arise

1.98

 emerges

1.89

 emergence

1.81

 arises

1.81

 arose

1.76

 emerging

1.73

emer

1.67

 arisen

1.65

Activations Density 0.694%

concepts related to discrepancies or disagreements in studies or reports

preceding a problem or situation

problem or emergence

No Comments

No Known Activations