INDEX

Explanations

phrases indicating information or statements made by someone

oai_token-act-pair · gpt-3.5-turbo

phrases that convey reported speech or statements

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

ettlement

-0.71

teness

-0.67

iots

-0.60

Zone

-0.59

 Jackets

-0.58

ments

-0.58

 Submission

-0.58

 perspective

-0.56

 Perspective

-0.56

ucks

-0.56

POSITIVE LOGITS

ª

0.85

 proport

0.75

ÙĦ

0.70

 ingred

0.67

ÙĨ

0.65

 anecd

0.65

ocry

0.63

ļé

0.63

¿

0.62

 Spiegel

0.62

Activations Density 0.107%

phrases indicating information or statements made by someone

phrases that convey reported speech or statements

No Comments

No Known Activations