INDEX

Explanations

proper nouns and academic institutions

oai_token-act-pair · gpt-3.5-turbo

references to specific institutions or organizations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

************

-0.77

advertisement

-0.73

UAL

-0.73

CPC

-0.66

Favorite

-0.63

UCT

-0.60

 Carbuncle

-0.58

~~

-0.58

Thirty

-0.58

Minecraft

-0.57

POSITIVE LOGITS

 Ober

1.33

lander

1.00

meyer

0.99

stad

0.99

keley

0.98

liga

0.97

thal

0.94

lin

0.93

omination

0.88

alis

0.85

Activations Density 0.006%

proper nouns and academic institutions

references to specific institutions or organizations

No Known Activations