INDEX

Explanations

questions or prompts starting with "Does"

oai_token-act-pair · gpt-3.5-turbo

questions that begin with "Does."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Islands

-0.74

rets

-0.73

 Canal

-0.70

haul

-0.68

 Typhoon

-0.67

 Ascension

-0.67

 palms

-0.67

bush

-0.66

boards

-0.66

 Methods

-0.64

POSITIVE LOGITS

omething

1.11

berra

0.91

paces

0.87

VIDIA

0.82

hift

0.81

omorphic

0.81

ettings

0.80

ometimes

0.80

onga

0.80

pace

0.79

Activations Density 0.042%

questions or prompts starting with "Does"

questions that begin with "Does."

No Comments

No Known Activations