INDEX

Explanations

keywords related to technical specifications or instructions

oai_token-act-pair · gpt-3.5-turbo

terms related to reports, features, and accounts in a technical or business context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĻĤ

-0.79

etheless

-0.77

 toget

-0.73

rising

-0.72

antically

-0.72

 democr

-0.72

iscopal

-0.71

ischer

-0.71

 exting

-0.71

 tremend

-0.68

POSITIVE LOGITS

 Manager

1.28

 Disorder

1.24

 Agreement

1.20

 Units

1.20

 Facility

1.19

 Initiative

1.19

 Month

1.17

 Definition

1.16

 Index

1.14

âĦ¢

1.14

Activations Density 0.387%

keywords related to technical specifications or instructions

terms related to reports, features, and accounts in a technical or business context

No Comments

No Known Activations