INDEX

Explanations

structured data or highlights from summary sections

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

Rare or unusual characters

np_acts-logits-general · gemini-2.0-flash

none, idx, Conservation, trapped

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 myſelf

-1.23

 itſelf

-1.22

 Majefty

-1.12

 Monfieur

-1.10

 pleaſure

-1.06

 purpoſe

-1.03

 Houſe

-1.03

 uſe

-1.03

 houſe

-1.03

 faſt

-1.02

POSITIVE LOGITS

0.59

 tekem

0.54

0.52

GOTREF

0.51

0.50

辰

0.50

le

0.50

da

0.50

0.49

Activations Density 0.021%

structured data or highlights from summary sections

Rare or unusual characters

none, idx, Conservation, trapped

No Comments

No Known Activations