INDEX

Explanations

phrases related to actions, experiences, and thoughts of people

oai_token-act-pair · gpt-3.5-turbo

expressions of measurement related to people's actions and outcomes

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

>>>>>>>>

-0.58

Zup

-0.52

theless

-0.52

 notwithstanding

-0.50

gallery

-0.48

 Marino

-0.48

bilt

-0.46

hov

-0.46

 Moder

-0.45

Yon

-0.45

POSITIVE LOGITS

 actually

0.54

 otherwise

0.53

 interacted

0.53

 currently

0.53

 desired

0.52

 perceive

0.51

 deems

0.50

 supposedly

0.50

 perce

0.49

 congreg

0.49

Activations Density 0.690%

phrases related to actions, experiences, and thoughts of people

expressions of measurement related to people's actions and outcomes

No Comments

No Known Activations