INDEX

Explanations

phrases that indicate potential outcomes or conditions, particularly in relation to medical or procedural contexts

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

Follows forms of the verb "to be"

np_acts-logits-general · gemini-2.0-flash

be + past participle

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

 Umum

-0.48

guiente

-0.47

 surla

-0.46

 brosse

-0.45

 Komple

-0.43

Bibli

-0.43

ablemente

-0.43

 gainera

-0.42

ambién

-0.42

новништво

-0.42

POSITIVE LOGITS

AddTagHelper

0.51

 Italijani

0.48

ValueStyle

0.47

DockStyle

0.47

HasAnnotation

0.46

 invokingState

0.45

 evident

0.42

VIAF

0.41

 CascadeType

0.40

DataSnapshot

0.40

Activations Density 0.575%

phrases that indicate potential outcomes or conditions, particularly in relation to medical or procedural contexts

Follows forms of the verb "to be"

be + past participle

No Comments

No Known Activations

phrases that indicate potential outcomes or conditions, particularly in relation to medical or procedural contexts

Follows forms of the verb "to be"

be + past participle

No Comments

No Known Activations