INDEX

Explanations

instances of "next" and related phrases indicating progression or future steps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 myſelf

-0.70

новништво

-0.58

ſelves

-0.55

 abſ

-0.54

 isolado

-0.53

 ſtand

-0.53

 uſed

-0.52

 himſelf

-0.52

 raiſ

-0.52

 Paglinawan

-0.51

POSITIVE LOGITS

 next

1.40

next

1.31

Next

1.27

 Next

1.24

 NEXT

1.13

NEXT

1.13

 nästa

0.99

 nächste

0.98

 nächsten

0.95

NextPage

0.95

Activations Density 0.481%

instances of "next" and related phrases indicating progression or future steps

No Comments

No Known Activations