INDEX

Explanations

references to various lists and listings in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 esternos

-0.66

 оригіналу

-0.63

CGRectMake

-0.60

 contextLoads

-0.60

ViewType

-0.59

CROSSTALK

-0.59

makeText

-0.59

uxxxx

-0.59

createComponent

-0.59

ThemeOverlay

-0.58

POSITIVE LOGITS

 list

1.85

 lists

1.65

 List

1.53

 liste

1.48

 Lists

1.46

 LIST

1.41

 lista

1.40

 Liste

1.39

List

1.33

 список

1.28

Activations Density 0.141%

references to various lists and listings in text

No Comments

No Known Activations