INDEX

Explanations

mentions of different types of mushrooms

oai_token-act-pair · gpt-3.5-turbo

terms related to mushrooms and fungi

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

points

-0.71

vent

-0.70

bred

-0.67

uers

-0.67

raught

-0.66

NEY

-0.66

enting

-0.65

dimensional

-0.64

mand

-0.64

PUT

-0.64

POSITIVE LOGITS

 mushrooms

1.19

 mushroom

0.99

 Mush

0.99

ccoli

0.98

atoes

0.94

lio

0.94

 Mushroom

0.93

 fungi

0.89

 Flavoring

0.86

iture

0.85

Activations Density 0.010%

mentions of different types of mushrooms

terms related to mushrooms and fungi

No Comments

No Known Activations