INDEX

Explanations

negations and conditional phrases

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

Follows "to" or a single-letter token

np_acts-logits-general · gemini-2.0-flash

verbs of being or occurrence

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

 Majefty

-0.81

Portail

-0.74

 myſelf

-0.73

 chofe

-0.72

ſelf

-0.70

 leaſt

-0.70

 ſind

-0.69

 pleaſure

-0.69

 uſe

-0.69

 onAnimation

-0.69

POSITIVE LOGITS

 consist

0.81

 occur

0.79

 entail

0.68

 serve

0.67

 happen

0.65

 contain

0.64

 ocur

0.64

 constitute

0.64

 arise

0.63

 comprise

0.62

Activations Density 0.865%

negations and conditional phrases

Follows "to" or a single-letter token

verbs of being or occurrence

No Comments

No Known Activations