INDEX

Explanations

references to meetings and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

лага

-0.51

olev

-0.50

hoy

-0.48

 Василь

-0.47

boldsymbol

-0.47

 faut

-0.47

 brands

-0.46

ushka

-0.46

wat

-0.45

is

-0.45

POSITIVE LOGITS

 meetings

1.67

 Meetings

1.56

Meetings

1.53

meetings

1.41

 visits

1.32

 outings

1.26

 Visits

1.25

 dinners

1.24

 trips

1.21

 afternoons

1.21

Activations Density 0.220%

references to meetings and discussions

No Comments

No Known Activations