INDEX

Explanations

individual names and locations

oai_token-act-pair · gpt-3.5-turbo

references to travel-related topics or plans

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 favors

-1.00

colored

-0.91

rollment

-0.90

 favor

-0.89

bors

-0.88

defense

-0.88

 honors

-0.87

 Ortiz

-0.87

caliber

-0.86

avored

-0.86

POSITIVE LOGITS

 apologise

1.42

 Â£

1.42

 recognise

1.42

 Labour

1.40

 organising

1.38

 realise

1.34

 emphas

1.31

NHS

1.30

 recognised

1.30

 apologised

1.29

Activations Density 1.166%

individual names and locations

references to travel-related topics or plans

No Comments

No Known Activations