INDEX

Explanations

technical terms related to performance metrics and computer science concepts

oai_token-act-pair · gpt-3.5-turbo

references to statistics and questions about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ails

-0.51

oa

-0.49

 delet

-0.49

 unus

-0.48

rez

-0.48

enary

-0.48

 stret

-0.48

sue

-0.47

en

-0.47

 impe

-0.47

POSITIVE LOGITS

 Specifically

0.65

 Cosponsors

0.64

 Firstly

0.63

 partName

0.62

Specifically

0.61

 Factors

0.61

Ô

0.61

OHN

0.59

åĮ

0.58

âĹ¼

0.58

Activations Density 0.964%

technical terms related to performance metrics and computer science concepts

references to statistics and questions about various subjects

No Comments

No Known Activations