INDEX

Explanations

segments of text with programming or mathematical notation, particularly those related to equations and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Roskov

-0.72

gameserver

-0.63

 MessageBoxIcon

-0.63

complexType

-0.62

 BorderRadius

-0.62

 numberWith

-0.62

]")]

-0.60

 '\\;'

-0.60

 createState

-0.59

васто

-0.59

POSITIVE LOGITS

richTextPanel

0.61

didSet

0.59

ыгана

0.57

 Offisielt

0.56

 VIDEOTAPE

0.56

 estimés

0.55

országban

0.54

 صوتيه

0.53

بالإنجليزية

0.52

لينكات

0.52

Activations Density 0.476%

segments of text with programming or mathematical notation, particularly those related to equations and functions

No Comments

No Known Activations