INDEX

Explanations

phrases emphasizing 'nothing' or its variations, indicating negation or absence

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

"Nothing" followed by comparative words

np_acts-logits-general · gemini-2.0-flash

nothing followed by qualifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

IndentedString

-0.70

WriteTagHelper

-0.63

}{@

-0.61

expandindo

-0.60

 houſe

-0.59

UnusedPrivate

-0.59

 Oldest

-0.59

Hauptartikel

-0.58

(&:

-0.58

 himſelf

-0.58

POSITIVE LOGITS

 else

0.91

 more

0.81

 special

0.77

 substantial

0.72

burger

0.67

new

0.66

but

0.66

 significant

0.64

 substantive

0.64

else

0.61

Activations Density 0.084%

phrases emphasizing 'nothing' or its variations, indicating negation or absence

"Nothing" followed by comparative words

nothing followed by qualifiers

No Comments

No Known Activations