INDEX

Explanations

negative statements or denials

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

Negation and uncertainty markers

np_acts-logits-general · gemini-2.0-flash

not any

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 relatively

-0.69

 only

-0.67

 Relatively

-0.63

完全に

-0.62

 piuttosto

-0.62

 somewhat

-0.60

 mostly

-0.59

 plutôt

-0.58

somewhat

-0.57

 fairly

-0.56

POSITIVE LOGITS

有任何

0.99

any

0.97

 nicio

0.97

 EVER

0.91

 ever

0.87

 jemals

0.86

 whatsoever

0.84

ANY

0.84

 alcun

0.81

Any

0.80

Activations Density 0.580%

negative statements or denials

Negation and uncertainty markers

not any

No Comments

No Known Activations