INDEX

Explanations

terms related to the acronym "MS" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to Microsoft products and services

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

============

-0.71

rer

-0.69

footed

-0.68

faced

-0.67

========

-0.67

falls

-0.65

 happiest

-0.64

rers

-0.63

fall

-0.60

bidden

-0.60

POSITIVE LOGITS

RP

1.15

CL

1.01

aunders

0.99

NBC

0.95

gt

0.93

DOS

0.91

AA

0.91

ettings

0.87

essor

0.87

NA

0.86

Activations Density 0.024%

terms related to the acronym "MS" in various contexts

references to Microsoft products and services

No Comments

No Known Activations