INDEX

Explanations

references related to the person Edward Snowden

oai_token-act-pair · gpt-3.5-turbo

references to Edward Snowden and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ptive

-0.76

ogun

-0.73

sembly

-0.70

 Dominion

-0.69

alities

-0.69

eto

-0.69

 denomin

-0.68

odge

-0.68

ombo

-0.67

vice

-0.66

POSITIVE LOGITS

 Snowden

1.01

 revelations

0.85

Leaks

0.82

 Archive

0.79

 whistleblower

0.78

DragonMagazine

0.77

NSA

0.76

 whistlebl

0.76

 trove

0.76

 whistleblowers

0.75

Activations Density 0.031%

references related to the person Edward Snowden

references to Edward Snowden and related terms

No Comments

No Known Activations