INDEX

Explanations

abbreviations related to the term "MS"

oai_token-act-pair · gpt-3.5-turbo

references to Microsoft-related terms or products

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rer

-0.75

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

-0.70

rers

-0.69

redo

-0.67

footed

-0.66

ries

-0.66

========

-0.65

 happiest

-0.64

 vind

-0.62

 damned

-0.62

POSITIVE LOGITS

RP

1.18

NBC

1.07

aunders

0.99

DOS

0.93

gt

0.92

AA

0.88

CL

0.88

VC

0.85

essor

0.84

DN

0.83

Activations Density 0.029%

abbreviations related to the term "MS"

references to Microsoft-related terms or products

No Comments

No Known Activations