INDEX

Explanations

keywords related to differences or diversions

oai_token-act-pair · gpt-3.5-turbo

terms related to differences and variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OHN

-0.80

FUL

-0.73

ÃįÃį

-0.71

CHO

-0.70

matic

-0.70

Accessory

-0.70

ctica

-0.69

Demand

-0.68

fulness

-0.68

äºĶ

-0.67

POSITIVE LOGITS

icult

1.49

iculty

1.31

erence

1.11

erences

1.05

inished

1.02

raction

0.98

diff

0.95

idence

0.91

racted

0.91

eree

0.89

Activations Density 0.015%

keywords related to differences or diversions

terms related to differences and variations

No Comments

No Known Activations