INDEX

Explanations

patterns related to statistical data

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 ویکی‌پدی

-0.54

RegressionTest

-0.52

ViewImports

-0.49

 كومونز

-0.49

页面存档备份

-0.47

 виправивши

-0.47

TagMode

-0.45

новништво

-0.45

 perú

-0.45

parsedMessage

-0.45

POSITIVE LOGITS

rash

0.47

ا

0.46

Rox

0.46

ronom

0.46

 ratio

0.46

bsch

0.46

0.45

apha

0.45

 bisogna

0.45

Activations Density 0.484%

patterns related to statistical data

No Known Activations