INDEX

Explanations

cryptic or encoded data formats and programming-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 parachoque

-0.51

 pungkas

-0.50

 Bucure

-0.49

 dumne

-0.49

 terdekat

-0.48

 îns

-0.47

 Gesellschaft

-0.47

 dianteira

-0.47

 democrática

-0.47

EndGlobalSection

-0.47

POSITIVE LOGITS

 Normdatei

0.65

BufferException

0.59

 dAtA

0.56

IsContent

0.55

addContainerGap

0.51

WriteTagHelper

0.48

InputBorder

0.45

 ModelExpression

0.45

 PeEnEo

0.45

tagHelperRunner

0.45

Activations Density 0.651%

cryptic or encoded data formats and programming-related terms

No Comments

No Known Activations