INDEX

Explanations

references to milk and dairy products

oai_token-act-pair · gpt-3.5-turbo

references to milk

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

angers

-0.88

SPONSORED

-0.83

izons

-0.80

asio

-0.79

âĸ¬

-0.72

 satell

-0.69

ISE

-0.68

nces

-0.68

 WATCHED

-0.67

vernment

-0.67

POSITIVE LOGITS

weed

1.10

 milk

1.00

waukee

0.98

maid

0.98

 Milk

0.93

mil

0.90

fed

0.87

tub

0.82

 chocolate

0.82

erton

0.82

Activations Density 0.012%

references to milk and dairy products

references to milk

No Comments

No Known Activations