INDEX

Explanations

phrases indicating purpose or intent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 therefor

-0.54

 sucede

-0.53

 propOrder

-0.52

 StatelessWidget

-0.49

 necesariamente

-0.49

 publicitaires

-0.47

 preocu

-0.47

 weeks

-0.46

 torno

-0.46

那么

-0.45

POSITIVE LOGITS

 simplicity

1.18

 convenience

1.16

 ease

1.12

 clarity

1.01

convenience

0.96

 easier

0.94

 brevity

0.85

 readability

0.85

 sake

0.84

 completeness

0.83

Activations Density 0.605%

phrases indicating purpose or intent

No Comments

No Known Activations