INDEX

Explanations

medical terms and concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to medical conditions and personal identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Niet

-0.44

 Democr

-0.42

jri

-0.41

Topics

-0.40

senal

-0.39

 Azerb

-0.39

 undermin

-0.39

uyomi

-0.39

 disadvant

-0.38

gom

-0.38

POSITIVE LOGITS

 âĢº

0.52

Â¶

0.46

º

0.39

][

0.37

atoon

0.36

hon

0.36

 Originally

0.35

hall

0.35

weed

0.35

Ê

0.35

Activations Density 1.820%

medical terms and concepts

terms related to medical conditions and personal identity

No Comments

No Known Activations