INDEX

Explanations

HTML and XML attributes, particularly those that include equal signs

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

UrlResolution

-0.49

webElementGuid

-0.43

 aapt

-0.42

WebpackPlugin

-0.42

تقاوى

-0.40

 resourceCulture

-0.40

Geplaatst

-0.40

ngrx

-0.40

oltre

-0.40

CD

-0.39

POSITIVE LOGITS

setVerticalGroup

0.55

 vuitton

0.50

 Cinematic

0.45

 ministerial

0.44

straints

0.43

bouquet

0.42

 דבר

0.42

 yrity

0.41

extAlignment

0.40

 tapaht

0.40

Activations Density 0.003%

HTML and XML attributes, particularly those that include equal signs

No Comments

No Known Activations