INDEX

Explanations

instances of the word "all" indicating inclusivity or totality within contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Monfieur

-0.79

 Houſe

-0.77

 itſelf

-0.74

DCM

-0.70

 Inſ

-0.69

Efq

-0.69

 cdti

-0.67

Eſ

-0.67

 Theſe

-0.66

 Тогда

-0.65

POSITIVE LOGITS

all

3.68

ALL

2.48

All

2.46

All

2.29

all

2.10

 semua

2.02

 todas

1.86

 все

1.83

 всех

1.77

 tutte

1.74

Activations Density 0.137%

instances of the word "all" indicating inclusivity or totality within contexts

No Comments

No Known Activations