INDEX

Explanations

negative statements or denials

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

"no" preceding a noun

np_acts-logits-general · gemini-2.0-flash

no followed by a word

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

SourceChecksum

-0.75

PhysRevD

-0.70

TagMode

-0.70

OOTDTY

-0.64

tamment

-0.63

PullParser

-0.58

 Cæsar

-0.58

 ostavi

-0.56

 disambiguazione

-0.55

tadır

-0.54

POSITIVE LOGITS

any

0.53

ydon

0.48

0.47

 Shame

0.47

an

0.46

معلومات

0.46

ühm

0.46

</thead>

0.46

 healthiest

0.45

igno

0.45

Activations Density 0.141%

negative statements or denials

"no" preceding a noun

no followed by a word

No Comments

No Known Activations