INDEX

Explanations

expressions of sadness or disappointment

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

expressing sadness or misfortune

np_acts-logits-general · gemini-2.0-flash

sadness and misfortune

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

IntoConstraints

-0.54

 '\\;'

-0.53

########.

-0.51

AnchorStyles

-0.51

AddTagHelper

-0.51

queryInterface

-0.50

ylvania

-0.49

:✨

-0.49

 HFILL

-0.49

LabelTagHelper

-0.48

POSITIVE LOGITS

sad

1.21

 sadly

1.15

 unfortunately

1.12

 Sadly

1.10

Sadly

1.07

unfortunately

1.07

 purtroppo

1.05

Sad

1.05

sad

1.05

Sad

1.03

Activations Density 0.143%

expressions of sadness or disappointment

expressing sadness or misfortune

sadness and misfortune

No Known Activations