INDEX

Explanations

the word "not"

oai_token-act-pair · gemini-2.0-flash

not

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

either

-0.67

not

-0.62

 Either

-0.62

 همچ

-0.60

Either

-0.60

+#+#

-0.57

still

-0.56

not

-0.55

 AssemblyProduct

-0.55

 either

-0.55

POSITIVE LOGITS

 necessarily

0.82

yet

0.65

orious

0.61

 only

0.61

 seulement

0.58

 always

0.57

uxxxx

0.57

 ashamed

0.56

Yet

0.56

ICES

0.53

Activations Density 2.268%

the word "not"

not

No Comments

No Known Activations