INDEX

Explanations

repeated phrases indicating intention or willingness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Personensuche

-0.85

ⓧ

-0.78

IndentedString

-0.76

Portály

-0.73

GEBURTSDATUM

-0.70

Geplaatst

-0.68

 rempliss

-0.68

 venait

-0.67

 feroit

-0.66

تفصیلات

-0.65

POSITIVE LOGITS

 have

0.72

 take

0.68

 will

0.67

 make

0.67

 توانید

0.66

can

0.65

0.64

“

0.61

 could

0.61

.~(\

0.60

Activations Density 0.527%

repeated phrases indicating intention or willingness

No Comments

No Known Activations