INDEX

Explanations

words and phrases related to connections and associations in scientific contexts

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

Filmographie

-0.47

guisement

-0.45

Soorten

-0.44

 оригіналу

-0.43

 layui

-0.43

PendingIntent

-0.43

Autoritní

-0.42

GTK

-0.41

لمين

-0.41

Etimología

-0.41

POSITIVE LOGITS

 дописавши

0.51

 estekak

0.49

 other

0.44

enterOuterAlt

0.43

 FetchType

0.40

 autres

0.40

 diğer

0.40

 linkovi

0.39

autres

0.38

 altre

0.38

Activations Density 0.138%

words and phrases related to connections and associations in scientific contexts

No Comments

No Known Activations