INDEX

Explanations

terms that imply significance or importance in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

awtextra

-0.73

 geldig

-0.67

ArgsConstructor

-0.64

 EconPapers

-0.63

 nakalista

-0.62

 useState

-0.60

EndContext

-0.59

WebVitals

-0.55

ंदीखरीदारी

-0.53

isContained

-0.53

POSITIVE LOGITS

 future

0.98

 permanent

0.90

future

0.81

 longterm

0.78

 Permanent

0.77

 Future

0.76

 long

0.76

permanent

0.76

Future

0.75

Permanent

0.75

Activations Density 0.434%

terms that imply significance or importance in text

No Comments

No Known Activations