INDEX

Explanations

phrases with person names

oai_token-act-pair · gpt-3.5-turbo

the character "ľ" appearing 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 favor

-0.94

 favour

-0.93

 spir

-0.87

 territorial

-0.82

 reflex

-0.80

 targeted

-0.78

 metic

-0.78

 taboo

-0.77

 carrier

-0.76

 wagon

-0.75

POSITIVE LOGITS

Because

1.56

They

1.54

It

1.46

And

1.46

But

1.45

That

1.43

He

1.43

Secondly

1.42

If

1.42

Otherwise

1.41

Activations Density 0.124%

phrases with person names

the character "ľ" appearing in various contexts

No Comments

No Known Activations