INDEX

Explanations

repetitions of the word "more."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Caballero

-0.78

 africana

-0.78

SNL

-0.78

bufio

-0.74

(&:

-0.72

 aguj

-0.69

Discografia

-0.68

 Lohan

-0.68

 majeur

-0.68

❥

-0.67

POSITIVE LOGITS

 more

2.09

 MORE

1.77

more

1.72

 More

1.65

More

1.61

MORE

1.54

emore

1.28

 lebih

1.26

 Moreno

1.24

Più

1.19

Activations Density 0.138%

repetitions of the word "more."

No Comments

No Known Activations