INDEX

Explanations

terms related to organizations or entities, specifically focusing on security vulnerabilities, regulations, and trade activities

oai_token-act-pair · gpt-3.5-turbo

acronyms or abbreviations associated with organizations or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 awoken

-0.70

 halves

-0.68

 tion

-0.65

nces

-0.64

heimer

-0.64

chers

-0.62

perse

-0.61

doors

-0.60

 Ashton

-0.59

enegger

-0.58

POSITIVE LOGITS

RM

1.10

TN

1.05

Bs

1.05

CV

1.03

AN

1.00

EB

0.99

BG

0.99

RF

0.99

MN

0.99

OE

0.98

Activations Density 0.098%

terms related to organizations or entities, specifically focusing on security vulnerabilities, regulations, and trade activities

acronyms or abbreviations associated with organizations or reports

No Comments

No Known Activations