INDEX

Explanations

years or dates

oai_token-act-pair · gpt-3.5-turbo

mentions of specific years

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

 stead

-0.78

hed

-0.75

kell

-0.70

lass

-0.67

aws

-0.65

orney

-0.64

aden

-0.64

bor

-0.63

armed

-0.62

ambers

-0.62

POSITIVE LOGITS

å¹

1.26

 edition

0.81

 Edition

0.80

0.79

âĢ²

0.75

 EDITION

0.74

 onwards

0.70

âĨĳ

0.70

 Remastered

0.68

 Nobel

0.67

Activations Density 0.122%

years or dates

mentions of specific years

No Comments

No Known Activations