INDEX

Explanations

phrases that denote specifications or conditions in legal or formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

StoryboardSegue

-0.94

 pinulongan

-0.71

 sumpay

-0.70

 betweenstory

-0.65

Tazama

-0.62

tvguidetime

-0.61

 كومونز

-0.59

Portale

-0.59

SerializedName

-0.58

 tiguan

-0.58

POSITIVE LOGITS

or

0.48

fecture

0.45

rrggbb

0.45

visão

0.45

eratops

0.43

 Câmara

0.43

 ویکی

0.42

 дописавши

0.41

setas

0.41

ไง

0.40

Activations Density 0.370%

phrases that denote specifications or conditions in legal or formal contexts

No Comments

No Known Activations