INDEX

Explanations

conditional phrases and questions related to decision-making or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ChildScrollView

-0.67

 unknownFields

-0.60

<bos>

-0.56

forKey

-0.51

getSupport

-0.50

hoof

-0.48

__;

-0.47

уна

-0.46

nonatomic

-0.45

 CGRectMake

-0.45

POSITIVE LOGITS

IVEREF

0.93

Tembelea

0.73

 nahilalakip

0.64

ंदीखरीदारी

0.64

 AssemblyProduct

0.61

 EconPapers

0.60

BeginContext

0.60

 sauvages

0.56

 propOrder

0.56

Петербург

0.56

Activations Density 0.290%

conditional phrases and questions related to decision-making or actions

No Comments

No Known Activations