INDEX

Explanations

structured data representations, particularly arrays and nested lists

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

gameserver

-0.65

googleapis

-0.64

fillType

-0.64

{}".

-0.61

bür

-0.61

kmale

-0.59

tagHelper

-0.59

\}^{

-0.59

 inter

-0.57

WEBPACK

-0.57

POSITIVE LOGITS

:✨

0.64

omores

0.63

,,,,

0.60

 >=",

0.57

 Coronel

0.57

","","

0.56

Zeneca

0.56

":[{

0.53

 myſelf

0.52

 benzina

0.51

Activations Density 0.231%

structured data representations, particularly arrays and nested lists

No Comments

No Known Activations