INDEX

Explanations

phrases indicating suitability or ideal conditions for products, scenarios, or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

jspx

-0.62

MessageOf

-0.61

MLLoader

-0.58

ynb

-0.57

TableBody

-0.57

\{\\

-0.56

ViewFeatures

-0.56

WebElementEntity

-0.55

ConverterFactory

-0.55

 okuyayım

-0.53

POSITIVE LOGITS

 geeignet

0.72

for

0.65

anskje

0.54

 sekali

0.54

 laid

0.50

 banget

0.50

 hvis

0.50

 beginner

0.50

 complement

0.49

 jeśli

0.49

Activations Density 0.238%

phrases indicating suitability or ideal conditions for products, scenarios, or services

No Comments

No Known Activations