INDEX

Explanations

references to slides, presentations, or visual aids

oai_token-act-pair · gpt-3.5-turbo

instances of the word "slide" and references to presentations or visual aids

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

orate

-0.90

omes

-0.79

OME

-0.75

raising

-0.75

etheless

-0.74

relevant

-0.70

 Carbuncle

-0.68

sts

-0.67

ilee

-0.65

orable

-0.64

POSITIVE LOGITS

itzer

0.80

 slide

0.79

 downhill

0.79

boards

0.76

 Canaver

0.76

 slope

0.76

iblings

0.75

ulic

0.75

creen

0.74

board

0.73

Activations Density 0.032%

references to slides, presentations, or visual aids

instances of the word "slide" and references to presentations or visual aids

No Comments

No Known Activations