INDEX

Explanations

words related to publications and blog posts

oai_token-act-pair · gpt-3.5-turbo

the end of text markers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Reef

-0.65

milo

-0.63

 Allied

-0.60

 stacks

-0.60

 Lauder

-0.59

Osc

-0.58

 baskets

-0.58

 Samar

-0.57

 Lama

-0.56

 Patriarch

-0.56

POSITIVE LOGITS

ources

1.03

lightly

0.98

aved

0.93

atisf

0.90

ELF

0.89

ued

0.89

ushi

0.88

omew

0.87

urgical

0.86

pecially

0.85

Activations Density 0.092%

words related to publications and blog posts

the end of text markers

No Comments

No Known Activations