INDEX

Explanations

commands or instructions starting with 'Let's'

oai_token-act-pair · gpt-3.5-turbo

repeated occurrences of a specific character or symbol

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

enegger

-0.81

 mathemat

-0.69

 horizont

-0.69

 undermin

-0.67

 tremend

-0.66

 seiz

-0.66

iannopoulos

-0.65

 lodging

-0.64

RIS

-0.62

 metast

-0.62

POSITIVE LOGITS

ı

1.03

Ľ

1.02

ĸ

1.01

ĵ

0.98

į

0.98

¡

0.97

ķ

0.97

£

0.96

º

0.94

¤

0.94

Activations Density 0.078%

commands or instructions starting with 'Let's'

repeated occurrences of a specific character or symbol

No Comments

No Known Activations