INDEX

Explanations

instances where both entities or concepts are mentioned or compared in a sentence

oai_token-act-pair · gpt-3.5-turbo

references to the word "Both."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

The

-0.79

Don

-0.77

All

-0.77

Ant

-0.75

No

-0.75

Can

-0.74

Dem

-0.74

See

-0.73

Got

-0.73

 Hand

-0.73

POSITIVE LOGITS

Although

1.63

Since

1.62

Indeed

1.62

Both

1.60

Though

1.58

Perhaps

1.56

Because

1.56

Fortunately

1.56

Unfortunately

1.55

Aside

1.55

Activations Density 0.115%

instances where both entities or concepts are mentioned or compared in a sentence

references to the word "Both."

No Comments

No Known Activations