INDEX

Explanations

phrases indicating possession or existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ſelf

-0.57

 betweenstory

-0.52

 itſelf

-0.47

ſelves

-0.45

 ſtate

-0.44

 ſhould

-0.43

 houſe

-0.42

istoitu

-0.39

 ſche

-0.39

Reprodução

-0.38

POSITIVE LOGITS

0.73

an

0.63

AnchorStyles

0.61

0.55

 cref

0.54

the

0.53

 regular

0.52

 olmayan

0.49

 Vertra

0.49

 برانيه

0.48

Activations Density 0.456%

phrases indicating possession or existence

No Comments

No Known Activations