INDEX

Explanations

phrases related to comparisons or lists of items

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate comparison or similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ople

-0.83

itiveness

-0.70

/+

-0.67

trap

-0.63

rous

-0.62

======

-0.61

atism

-0.60

\<

-0.59

aca

-0.59

orage

-0.58

POSITIVE LOGITS

 well

1.75

well

1.39

 opposed

1.13

pects

0.99

ynchron

0.95

part

0.95

ociated

0.90

ides

0.88

 diverse

0.88

 Well

0.87

Activations Density 0.121%

phrases related to comparisons or lists of items

phrases that indicate comparison or similarity

No Comments

No Known Activations