INDEX

Explanations

phrases indicating likelihood or probability

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

"Likely" or "unlikely" followed by "to"

np_acts-logits-general · gemini-2.0-flash

what is likely to happen

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

 apparently

-0.59

 allegedly

-0.50

 supposedly

-0.45

-0.44

 Apparently

-0.43

pageX

-0.43

ริง

-0.42

!("{

-0.42

 vital

-0.42

apparently

-0.42

POSITIVE LOGITS

 AssemblyCulture

1.10

hood

0.98

RenderAtEndOf

0.96

lihood

0.95

AsUp

0.95

pexpr

0.94

IntoConstraints

0.91

 MainAxisSize

0.91

corrência

0.88

المناصب

0.86

Activations Density 0.164%

phrases indicating likelihood or probability

"Likely" or "unlikely" followed by "to"

what is likely to happen

No Comments

No Known Activations