INDEX

Explanations

topics related to reading and books

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67

Prompts (Dashboard)

24,576 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

 autorytatywna

-0.72

BagConstraints

-0.62

LLocation

-0.56

rungsseite

-0.52

GEBURTS

-0.49

UpdateCommand

-0.47

setVerticalGroup

-0.46

 arşivlendi

-0.45

featureID

-0.45

ertos

-0.45

POSITIVE LOGITS

 reading

0.64

Reading

0.58

 olvas

0.57

 lectura

0.56

 read

0.55

 unread

0.53

阅读

0.52

 READING

0.51

 reread

0.51

 Reading

0.48

Activations Density 0.203%

topics related to reading and books

No Comments

No Known Activations