INDEX

Explanations

references to decision-making processes or actions taken by characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

UserScript

-0.69

 Paglinawan

-0.69

Vidite

-0.66

-0.61

áctenos

-0.61

findpost

-0.58

 AppModule

-0.57

RegistryLite

-0.57

PositiveButton

-0.56

يكب

-0.56

POSITIVE LOGITS

loroethene

0.55

 Season

0.51

 season

0.50

season

0.49

 Coach

0.48

 saison

0.47

Season

0.46

 promo

0.44

SEASON

0.43

 SEASON

0.42

Activations Density 0.141%

references to decision-making processes or actions taken by characters

No Comments

No Known Activations