INDEX

Explanations

phrases enclosed in quotation marks

oai_token-act-pair · gpt-3.5-turbo

repeated phrases or expressions within the text

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

ÄŁ

-0.86

DERR

-0.77

fman

-0.68

 Skydragon

-0.68

 Thro

-0.67

hari

-0.65

ntil

-0.65

elsen

-0.64

Fal

-0.63

llah

-0.63

POSITIVE LOGITS

ology

1.10

phrase

1.06

 phrases

0.95

 phrase

0.93

witz

0.87

stress

0.86

terday

0.83

 uttered

0.81

voy

0.80

atre

0.79

Activations Density 0.016%

phrases enclosed in quotation marks

repeated phrases or expressions within the text

No Comments

No Known Activations