INDEX

Explanations

words related to different levels, degrees, or sizes of a specific quality or characteristic

oai_token-act-pair · gpt-3.5-turbo

phrases indicating varying degrees of importance or quality

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

idav

-0.69

etsk

-0.67

skirts

-0.62

iso

-0.62

pes

-0.61

Shut

-0.60

Alv

-0.59

pta

-0.59

MAP

-0.58

plets

-0.58

POSITIVE LOGITS

 magnitude

1.11

 importance

1.05

 caliber

1.03

 proportions

0.99

course

0.96

 stature

0.95

 renown

0.90

 utmost

0.89

 origin

0.87

 calib

0.83

Activations Density 0.202%

words related to different levels, degrees, or sizes of a specific quality or characteristic

phrases indicating varying degrees of importance or quality

No Comments

No Known Activations