INDEX

Explanations

references to display technologies and their attributes

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

display notification or device

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

Chic

-0.47

 useRef

-0.44

 Chic

-0.42

EOF

-0.42

Vic

-0.42

 Linus

-0.42

tubers

-0.42

mich

-0.41

Koo

-0.41

 Coward

-0.41

POSITIVE LOGITS

 Display

0.61

 DISPLAY

0.59

DISPLAY

0.53

verwijspagina

0.51

Displays

0.49

 display

0.49

displays

0.49

 Displays

0.49

Displayed

0.47

protoimpl

0.47

Activations Density 0.022%

references to display technologies and their attributes

display notification or device

No Comments

No Known Activations