INDEX

Explanations

phrases that indicate relationships or evaluations within contexts, particularly focusing on data comparison and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 <=",

-0.46

setViewName

-0.46

 TextAlign

-0.44

DoubleQuotes

-0.42

 PARSER

-0.42

gameserver

-0.40

netbeans

-0.40

itre

-0.40

prepareStatement

-0.40

ibouti

-0.40

POSITIVE LOGITS

 other

4.29

other

3.73

Other

3.30

 Other

3.25

autres

3.24

 autres

3.18

 otros

3.18

 OTHER

3.13

 otras

3.08

 others

3.04

Activations Density 3.850%

phrases that indicate relationships or evaluations within contexts, particularly focusing on data comparison and experiences

No Comments

No Known Activations