INDEX

Explanations

mentions of ancient concepts or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 kaynağından

-0.64

 فريبيس

-0.59

infer

-0.57

 Fuse

-0.56

Infer

-0.52

findpost

-0.52

δας

-0.52

koh

-0.52

TabIndex

-0.51

 Tender

-0.51

POSITIVE LOGITS

 båda

0.79

Ambos

0.78

{}".

0.77

{}'.

0.76

 Both

0.76

 begge

0.75

 both

0.72

 ambos

0.72

{}",

0.71

 entrambi

0.71

Activations Density 0.109%

mentions of ancient concepts or ideas

No Comments

No Known Activations