INDEX

Explanations

terms related to the concept of arrival

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

><><

-0.54

жах

-0.50



-0.50

Fre

-0.49

urrent

-0.49

estacks

-0.48

CurrentValue

-0.48

Zing

-0.48

 sạn

-0.47

rpt

-0.47

POSITIVE LOGITS

Arri

2.45

 arrival

2.36

 Arri

2.25

 arrivals

2.25

 arrive

2.19

 arriving

2.17

 arrives

2.11

arrival

2.08

arri

2.08

 arrived

2.08

Activations Density 0.026%

terms related to the concept of arrival

No Comments

No Known Activations