INDEX

Explanations

elements of storytelling that describe actions and settings

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

 Theſe

-0.61

ValueStyle

-0.56

ſelves

-0.53

bootstrapcdn

-0.53

HasColumnType

-0.52

DockStyle

-0.51

ByDefault

-0.49

DispatchToProps

-0.49

Бахар

-0.49

moiselle

-0.49

POSITIVE LOGITS

 unaware

0.73

 unable

0.69

 unsure

0.66

 thankful

0.65

 seemingly

0.64

 hoping

0.62

 only

0.61

 oblivious

0.61

 grateful

0.61

 knowing

0.61

Activations Density 0.221%

elements of storytelling that describe actions and settings

No Comments

No Known Activations