INDEX

Explanations

terms related to participation and group dynamics in discussions or studies

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

possibility or uncertainty

np_acts-logits-general · gemini-2.0-flash

possibility or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

readFileSync

-0.56

ومة

-0.55

UnsafeEnabled

-0.53

ContentAlignment

-0.51

тных

-0.49

大好きです

-0.49

なんですが

-0.48

setContentType

-0.48

 NSCoder

-0.48

HttpServlet

-0.47

POSITIVE LOGITS

 might

3.01

may

2.93

 maybe

2.79

 possibly

2.67

might

2.66

 mungkin

2.66

maybe

2.56

 perhaps

2.52

 Possibly

2.52

possibly

2.49

Activations Density 1.963%

terms related to participation and group dynamics in discussions or studies

possibility or uncertainty

possibility or uncertainty

No Comments

No Known Activations