INDEX

Explanations

the word "what" in various contexts

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

Sentences/phrases beginning with "what"

np_acts-logits-general · gemini-2.0-flash

what is

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

esterno

-0.52

のかもしれません

-0.47

 Longo

-0.46

endregion

-0.45

DBA

-0.45

varlak

-0.44

popo

-0.44

 rowIndex

-0.44

 termica

-0.44

پیوند

-0.44

POSITIVE LOGITS

 what

1.34

what

1.22

What

1.20

 WHAT

1.12

 What

1.10

WHAT

1.05

 whats

0.82

whats

0.78

Cosa

0.65

Whats

0.65

Activations Density 0.159%

the word "what" in various contexts

Sentences/phrases beginning with "what"

what is

No Comments

No Known Activations