INDEX

Explanations

terms related to the development and growth of various traits or conditions

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

"Developed" followed by a noun

np_acts-logits-general · gemini-2.0-flash

developed a or an

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 halen

-0.49

Consts

-0.39

ビング

-0.39

GEBURTS

-0.38

try

-0.38

itoare

-0.38

ált

-0.38

 update

-0.38

 अभी

-0.38

<th>

-0.37

POSITIVE LOGITS

sizeCache

0.88

principalColumn

0.87

✨:

0.82

Morfologia

0.81

 Chwiliwch

0.81

DrawerToggle

0.80

complexContent

0.80

 nakalista

0.80

AndEndTag

0.77

 дописавши

0.76

Activations Density 0.204%

terms related to the development and growth of various traits or conditions

"Developed" followed by a noun

developed a or an

No Comments

No Known Activations