INDEX

Explanations

words starting with "EX"

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "EX" indicating exclusivity or special features

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

kson

-0.83

enance

-0.82

kowski

-0.77

¶ħ

-0.75

eworks

-0.72

erson

-0.70

tackle

-0.68

 Seym

-0.67

kamp

-0.66

yard

-0.66

POSITIVE LOGITS

CLUS

1.29

PRESS

1.24

TERN

1.23

PORT

1.19

CEPT

1.17

PER

1.14

ICO

1.00

TR

0.99

ACT

0.99

ERC

0.98

Activations Density 0.016%

words starting with "EX"

instances of the prefix "EX" indicating exclusivity or special features

No Comments

No Known Activations