INDEX

Explanations

capital letters and symbols in a specific pattern

oai_token-act-pair · gpt-3.5-turbo

a specific character or symbol used repeatedly in various contexts

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

 mathemat

-1.00

 disadvant

-0.89

 princ

-0.88

 satell

-0.85

 psychiat

-0.84

 predec

-0.83

 proport

-0.80

 neighb

-0.79

 arrang

-0.79

 agre

-0.78

POSITIVE LOGITS

ï¸ı

1.55

å¥³

1.01

çľ

0.95

 âĢº

0.95

âĶĢâĶĢ

0.94

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.92

âĶĢâĶĢâĶĢâĶĢ

0.89

éĩ

0.87

âĿ

0.85

à¥

0.84

Activations Density 0.202%

capital letters and symbols in a specific pattern

a specific character or symbol used repeatedly in various contexts

No Comments

No Known Activations