INDEX

Explanations

header information related to content types and transfer encoding in data formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

WindowConstants

-0.74

seigneur

-0.67

 Invis

-0.67

expandindo

-0.66

:+:

-0.66

 paroisse

-0.65

 Keats

-0.64

참고

-0.63

 piers

-0.63

 luon

-0.62

POSITIVE LOGITS

TestingModule

0.77

 للمعارف

0.70

ImageContext

0.67

 getContent

0.59

SpringBootTest

0.59

 MaterialApp

0.54

RTCK

0.54

 contents

0.53

BagConstraints

0.53

Conten

0.52

Activations Density 0.026%

header information related to content types and transfer encoding in data formats

No Comments

No Known Activations