INDEX

Explanations

phrases related to compensating for something, often a loss or mistake

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

FTWARE

-0.75

onomy

-0.73

-0.71

uggest

-0.67

soever

-0.67

chief

-0.66

fman

-0.63

raq

-0.63

haps

-0.62

oire

-0.61

POSITIVE LOGITS

 losses

1.36

 lost

1.35

 shortfall

1.21

 loss

1.10

missing

1.02

 Loss

0.97

 wasted

0.97

 deficiencies

0.95

 missing

0.95

 dwindling

0.93

Activations Density 0.159%

phrases related to compensating for something, often a loss or mistake

No Comments

No Known Activations