INDEX

Explanations

marketing or sponsorship mentions

oai_token-act-pair · gpt-3.5-turbo

specific characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Buyable

-0.78

 fortun

-0.73

 Palest

-0.69

çīĪ

-0.68

 guiActiveUnfocused

-0.68

 seiz

-0.66

BuyableInstoreAndOnline

-0.66

 Tanz

-0.65

 Objective

-0.62

 shack

-0.62

POSITIVE LOGITS

£

1.11

¼

1.05

¬

1.04

¤

1.02

¹

1.01

Ĵ

1.00

ª

1.00

ķ

0.99

ĸ

0.99

Ń

0.99

Activations Density 0.289%

marketing or sponsorship mentions

specific characters or symbols

No Comments

No Known Activations