INDEX

Explanations

the term "newly" associated with various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Horst

-0.86

 Horst

-0.82

ობ

-0.70

ImageContext

-0.69

 azzurro

-0.67

 Lourdes

-0.67

andExpect

-0.66

 totem

-0.66

цездатний

-0.65

 الرياضيه

-0.63

POSITIVE LOGITS

 newly

1.55

 Newly

1.50

newly

1.50

Newly

1.49

 freshly

1.03

 finely

0.96

 nowo

0.90

Datuak

0.89

 recém

0.81

 beautifully

0.78

Activations Density 0.117%

the term "newly" associated with various contexts

No Comments

No Known Activations