INDEX

Explanations

phrases related to individual differences

oai_token-act-pair · gpt-3.5-turbo

references to individual differences and variations in children

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

rollers

-0.78

ATA

-0.77

ãĥİ

-0.76

tsky

-0.71

der

-0.71

roller

-0.71

trak

-0.68

×ª

-0.67

Assembly

-0.64

stra

-0.64

POSITIVE LOGITS

 between

0.95

ials

0.93

between

0.91

iating

0.90

ially

0.88

yip

0.87

iveness

0.83

iculty

0.78

ensable

0.76

 Between

0.75

Activations Density 0.032%

phrases related to individual differences

references to individual differences and variations in children

No Comments

No Known Activations