INDEX

Explanations

references to specific individuals or entities, particularly relating to business or finance

oai_token-act-pair · gpt-3.5-turbo

references to Warren Buffett and his association with Berkshire Hathaway

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pter

-0.80

ĪĴ

-0.77

ories

-0.76

fully

-0.70

FTWARE

-0.69

ORY

-0.68

RT

-0.67

phis

-0.66

 skelet

-0.65

 psychiat

-0.65

POSITIVE LOGITS

 Buffett

1.16

etts

0.89

 Berkshire

0.81

 Hath

0.80

leneck

0.77

olini

0.76

 Buff

0.76

ulously

0.75

oken

0.75

 dividends

0.74

Activations Density 0.011%

references to specific individuals or entities, particularly relating to business or finance

references to Warren Buffett and his association with Berkshire Hathaway

No Comments

No Known Activations