INDEX

Explanations

buzzwords or trendy terms

oai_token-act-pair · gpt-3.5-turbo

terms related to "buzz" or excitement surrounding events, products, or announcements

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

tein

-0.74

©¶æ

-0.70

 restitution

-0.68

 antit

-0.67

 confisc

-0.65

 unjust

-0.64

 Barbar

-0.64

 Equality

-0.63

 unfit

-0.62

abama

-0.62

POSITIVE LOGITS

saw

1.12

 buzz

1.03

ards

1.01

arded

0.94

waves

0.94

worthy

0.93

atform

0.92

feed

0.89

INESS

0.88

vine

0.87

Activations Density 0.013%

buzzwords or trendy terms

terms related to "buzz" or excitement surrounding events, products, or announcements

No Comments

No Known Activations