INDEX

Explanations

terms related to the concept of "each" and general quantifications

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

Followed by "each" or "all"

np_acts-logits-general · gemini-2.0-flash

describing components of each

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 might

-0.46

can

-0.45

 wasn

-0.45

 mọi

-0.44

isn

-0.43

-0.42

 cambio

-0.42

may

-0.41

 puissent

-0.41

-0.40

POSITIVE LOGITS

 requiring

1.66

 needing

1.50

 having

1.35

 featuring

1.28

 containing

1.25

 possessing

1.25

 resembling

1.25

 relying

1.25

 nahilalakip

1.23

 consisting

1.23

Activations Density 0.484%

terms related to the concept of "each" and general quantifications

Followed by "each" or "all"

describing components of each

No Comments

No Known Activations