INDEX

Explanations

references to the name "Donald Trump"

oai_token-act-pair · gpt-3.5-turbo

mentions of Donald Trump

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.71

nexus

-0.70

pole

-0.69

MpServer

-0.68

 informants

-0.64

 arteries

-0.63

breeding

-0.62

DragonMagazine

-0.61

 corners

-0.60

NRS

-0.60

POSITIVE LOGITS

 Walsh

0.76

terness

0.75

ª

0.75

swer

0.74

 Pence

0.73

 Donald

0.73

mares

0.72

Taj

0.70

 Sutherland

0.69

 Abrams

0.69

Activations Density 0.029%

references to the name "Donald Trump"

mentions of Donald Trump

No Comments

No Known Activations