INDEX

Explanations

words related to personal experiences and emotional states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

rungsseite

-0.68

Truly

-0.59

Specifically

-0.57

Definitely

-0.57

Mainly

-0.56

Typically

-0.55

 Definitely

-0.55

Probably

-0.54

 TAMBÉM

-0.54

Really

-0.53

POSITIVE LOGITS

 ProtoMessage

0.65

 témoig

0.49

UAGES

0.48

 Maladies

0.47

RefNanny

0.46

سياسي

0.46

Cursors

0.46

utives

0.46

BibitemShut

0.45

省市镇

0.45

Activations Density 1.095%

words related to personal experiences and emotional states

No Comments

No Known Activations

words related to personal experiences and emotional states

No Comments

No Known Activations