INDEX

Explanations

phrases that introduce examples or excerpts

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

Followed by a determiner or a number

np_acts-logits-general · gemini-2.0-flash

here's an example

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

 للاسماء

-0.79

 ویکی‌پدی

-0.71

GEBURTSDATUM

-0.67

⟬

-0.65

:✨

-0.65

AndEndTag

-0.64

StructEnd

-0.64

 فريبيس

-0.63

yntaxException

-0.63

 arşivlendi

-0.62

POSITIVE LOGITS

how

0.69

 what

0.65

why

0.49

 hoping

0.46

what

0.46

How

0.45

 proof

0.45

how

0.44

 where

0.44

0.40

Activations Density 0.113%

phrases that introduce examples or excerpts

Followed by a determiner or a number

here's an example

No Comments

No Known Activations