INDEX

Explanations

mathematical notation and concepts related to transformations and variables

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

تقاوى

-1.29

 AssemblyCompany

-1.18

 ModelExpression

-1.10

 CreateTagHelper

-1.04

tagHelperRunner

-0.98

 Chwiliwch

-0.97

AndEndTag

-0.92

EndGlobalSection

-0.92

Personendaten

-0.92

 мәкал

-0.91

POSITIVE LOGITS

↵

0.54

).

0.52

[toxicity=0]

0.50

 […]

0.50

 appunto

0.50

etc

0.45

\\

0.43

‌

0.43

↵↵

0.42

).

0.41

Activations Density 31.199%

mathematical notation and concepts related to transformations and variables

No Known Activations