INDEX

Explanations

information related to leaked documents, whistleblowers, and espionage

oai_token-act-pair · gpt-3.5-turbo

references to significant leaks and revelations associated with WikiLeaks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

urally

-0.74

chairs

-0.72

OH

-0.71

iculture

-0.70

bred

-0.68

ttle

-0.67

opathic

-0.67

 neigh

-0.65

ural

-0.65

oba

-0.65

POSITIVE LOGITS

 trove

1.38

 revelations

1.37

 WikiLeaks

1.26

 Snowden

1.21

 exposing

1.19

Leaks

1.17

 whistlebl

1.16

 Wikileaks

1.16

 leaked

1.11

 disclosures

1.09

Activations Density 0.229%

information related to leaked documents, whistleblowers, and espionage

references to significant leaks and revelations associated with WikiLeaks

No Comments

No Known Activations