INDEX

Explanations

expressions of awareness, knowledge, and understanding regarding various subjects

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

 Photocase

-0.66

msgTypes

-0.59

 Wicidata

-0.57

 surla

-0.56

DIPSETTING

-0.54

 itſelf

-0.54

Autoritní

-0.53

MessageOf

-0.52

 informée

-0.51

 OMITBAD

-0.50

POSITIVE LOGITS

but

0.45

 schwier

0.45

我知道

0.41

 δύ

0.39

difficult

0.38

 moeili

0.38

KommentareTeilen

0.37

原始内容存档于

0.37

glBind

0.37

sur

0.35

Activations Density 0.202%

expressions of awareness, knowledge, and understanding regarding various subjects

No Comments

No Known Activations