INDEX

Explanations

phrases related to comparison, highlighting contrast or preference

oai_token-act-pair · gpt-3.5-turbo

comparative phrases that highlight the notion of preference or superiority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

yrim

-0.74

kan

-0.70

ortal

-0.68

awaru

-0.68

utenberg

-0.68

enos

-0.67

eri

-0.65

illet

-0.64

iren

-0.63

ero

-0.63

POSITIVE LOGITS

 necessarily

0.81

 anything

0.80

 worrying

0.73

 substance

0.66

 vice

0.64

nam

0.64

 appe

0.64

 merely

0.61

 something

0.61

 actual

0.61

Activations Density 0.200%

phrases related to comparison, highlighting contrast or preference

comparative phrases that highlight the notion of preference or superiority

No Comments

No Known Activations