INDEX

Explanations

specific Unicode characters

oai_token-act-pair · gpt-3.5-turbo

recurring patterns or phrases involving the concept of not

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 mathemat

-0.91

 Palestin

-0.81

 disadvant

-0.80

 lawy

-0.75

 contrace

-0.70

 misunder

-0.69

 fortun

-0.68

 predec

-0.67

 princ

-0.67

 Seym

-0.66

POSITIVE LOGITS

ï¸ı

1.26

âĶĢâĶĢ

0.81

ï¸

0.81

Â£

0.77

âĻ

0.76

own

0.73

âĶĢâĶĢâĶĢâĶĢ

0.69

âĤ¬

0.69

tre

0.68

Â°

0.68

Activations Density 0.304%

specific Unicode characters

recurring patterns or phrases involving the concept of not

No Comments

No Known Activations