INDEX

Explanations

phrases related to user experiences

oai_token-act-pair · gpt-3.5-turbo

references to user experience

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

laws

-0.69

law

-0.68

cmp

-0.67

roup

-0.67

anski

-0.67

nod

-0.66

inately

-0.65

 filings

-0.63

dy

-0.63

enta

-0.63

POSITIVE LOGITS

ually

0.89

iences

0.82

 Remastered

0.82

urable

0.79

 experien

0.74

 Experience

0.71

ULTS

0.71

terness

0.71

 experiences

0.71

Capture

0.70

Activations Density 0.049%

phrases related to user experiences

references to user experience

No Comments

No Known Activations