INDEX

Explanations

references to the company "General Motors" and related entities

oai_token-act-pair · gpt-3.5-turbo

mentions of automotive and technology companies, particularly General Motors and General Electric

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

GMT

-0.86

usc

-0.69

bound

-0.68

iable

-0.66

obin

-0.64

thread

-0.60

 Kenyan

-0.59

 aber

-0.59

ĥ

-0.59

ibilities

-0.58

POSITIVE LOGITS

 Corporation

0.95

 Stores

0.90

 Corp

0.89

bourg

0.79

 Foundation

0.75

 Ventures

0.74

 Industries

0.72

 Ammunition

0.72

 divest

0.72

merce

0.72

Activations Density 0.064%

references to the company "General Motors" and related entities

mentions of automotive and technology companies, particularly General Motors and General Electric

No Known Activations