INDEX

Explanations

phrases indicating conditions or exceptions in narratives

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

Following negative words

np_acts-logits-general · gemini-2.0-flash

negation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-0.76

kloped

-0.68

assertNull

-0.67

 propOrder

-0.65

#+#

-0.64

CppMethod

-0.64

 Aucune

-0.61

 Aucun

-0.61

PRNewswire

-0.59

 negligible

-0.58

POSITIVE LOGITS

not

1.98

isn

1.71

 bukan

1.67

not

1.66

 nicht

1.54

 aren

1.54

Not

1.47

不是

1.46

 wasn

1.41

Not

1.41

Activations Density 0.517%

phrases indicating conditions or exceptions in narratives

Following negative words

negation

No Comments

No Known Activations