INDEX

Explanations

phrases indicating significant events or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Abit

-0.50

 varandra

-0.45

 հղումներ

-0.45

 myſelf

-0.45

ambién

-0.43

 CallOverrides

-0.41

épreuve

-0.40

 generaciones

-0.39

 universidades

-0.39

 Monfieur

-0.39

POSITIVE LOGITS

warn

0.44

 writeTo

0.42

WARN

0.40

 warn

0.40

 last

0.39

充

0.38

 Last

0.38

TheReal

0.37

 warns

0.37

 Stroh

0.37

Activations Density 0.023%

phrases indicating significant events or milestones

No Comments

No Known Activations