INDEX

Explanations

terms and phrases related to public health and emergency communication

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

Follows "<start_of_turn>user"

np_acts-logits-general · gemini-2.0-flash

reflexive pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 dégust

-0.42

ThroughAttribute

-0.41

 anuales

-0.41

-0.37

 annuelle

-0.35

 caballos

-0.35

 Karriere

-0.35

 disfrute

-0.34

 transfieras

-0.33

 falleció

-0.33

POSITIVE LOGITS

ſelf

0.73

 faſt

0.69

 ſche

0.66

 myſelf

0.65

wiſe

0.65

دانشنامهٔ

0.65

 itſelf

0.65

ſelves

0.65

 himſelf

0.62

 ſta

0.62

Activations Density 0.082%

terms and phrases related to public health and emergency communication

Follows "<start_of_turn>user"

reflexive pronouns

No Comments

No Known Activations

terms and phrases related to public health and emergency communication

Follows "<start_of_turn>user"

reflexive pronouns

No Comments

No Known Activations