INDEX

Explanations

expressions of suspicion or concern, particularly in the context of discourse and decision-making

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

Followed by "about"

np_acts-logits-general · gemini-2.0-flash

talking about

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

TintMode

-0.60

RenderAtEndOf

-0.59

Personendaten

-0.59

TestingModule

-0.59

Zeneca

-0.59

AutoField

-0.58

ThemeOverlay

-0.57

BeginInit

-0.55

ándolos

-0.54

 parseFrom

-0.54

POSITIVE LOGITS

 about

3.92

about

2.70

About

2.35

 ABOUT

2.32

 About

2.21

 tentang

2.07

abt

1.75

 apie

1.73

ABOUT

1.68

 abou

1.66

Activations Density 0.849%

expressions of suspicion or concern, particularly in the context of discourse and decision-making

Followed by "about"

talking about

No Comments

No Known Activations