INDEX

Explanations

phrases that describe the actions or states of subjects in a context of announcements and statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

eaways

-0.59

 бывает

-0.56

 Schna

-0.55

werp

-0.55

 kebaikan

-0.53

 concess

-0.53

 Schnitt

-0.53

当たり前

-0.53

 parametros

-0.52

γεν

-0.52

POSITIVE LOGITS

 currently

0.93

currently

0.77

now

0.75

 attualmente

0.75

 reportedly

0.74

 actualmente

0.70

 presently

0.68

setVerticalGroup

0.68

 Currently

0.67

 nyní

0.66

Activations Density 0.290%

phrases that describe the actions or states of subjects in a context of announcements and statements

No Comments

No Known Activations