INDEX

Explanations

phrases related to expectations and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ValueStyle

-0.69

 future

-0.50

 Unless

-0.46

endt

-0.43

 Wiktionnaire

-0.43

æk

-0.43

 ghế

-0.43

 Future

-0.43

Future

-0.42

 corrente

-0.42

POSITIVE LOGITS

 longed

1.26

 давно

1.21

finally

1.17

 longtemps

1.16

 waited

1.14

一直

1.13

 dlouho

1.13

 long

1.12

 länge

1.11

 previously

1.10

Activations Density 0.302%

phrases related to expectations and outcomes

No Comments

No Known Activations