INDEX

Explanations

mentions of historical figures or events

oai_token-act-pair · gpt-3.5-turbo

instances of notable historical references or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 prepaid

-0.82

 ponies

-0.75

 shutdown

-0.74

 minion

-0.74

urances

-0.73

 pony

-0.73

 whine

-0.72

 refuel

-0.72

 scrim

-0.72

 fiat

-0.72

POSITIVE LOGITS

 Written

1.34

 Readers

1.30

 Preview

1.21

 Published

1.12

 Chapters

1.11

 Drawing

1.10

 Topics

1.09

 ISBN

1.08

 Contemporary

1.07

Written

1.05

Activations Density 0.456%

mentions of historical figures or events

instances of notable historical references or events

No Comments

No Known Activations