INDEX

Explanations

words and phrases associated with winning or achieving awards

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

subsubsection

-0.46

setLong

-0.44

 suis

-0.43

érale

-0.43

այ

-0.43

setInt

-0.42

Pop

-0.41

влению

-0.41

func

-0.40

amba

-0.40

POSITIVE LOGITS

 winning

1.63

 winners

1.58

 Winning

1.54

 winner

1.53

Winning

1.47

 wins

1.39

 Winners

1.35

 winnings

1.35

win

1.35

winning

1.32

Activations Density 0.140%

words and phrases associated with winning or achieving awards

No Comments

No Known Activations