INDEX

Explanations

discussions around moral and ethical dilemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

--

-1.73

�

-1.62

�

-1.58

"--

-1.52

---

-1.50



-1.47

-----

-1.34

)--

-1.33



-1.30

--"

-1.29

POSITIVE LOGITS

—

2.45

«

1.62

cbd

1.55

 —,

1.44

(«

1.35

anță

1.23

‌

1.18

»

1.18

«

1.13

»

1.11

Activations Density 0.934%

discussions around moral and ethical dilemmas

No Comments

No Known Activations