INDEX

Explanations

references to directors, episodes, and character interactions in TV shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Diweddarwch

-0.57

tagHelperRunner

-0.55

AutoField

-0.52

interopRequire

-0.51

(!__

-0.47

fas

-0.47

 Lust

-0.47

oleh

-0.47

┻

-0.46

 EconPapers

-0.46

POSITIVE LOGITS

 episode

0.73

EnableWeb

0.73

 episodic

0.69

episode

0.67

 episódio

0.65

 episodes

0.64

 CommonModule

0.60

Episode

0.60

WriteAttribute

0.59

 episodio

0.59

Activations Density 0.167%

references to directors, episodes, and character interactions in TV shows

No Comments

No Known Activations