INDEX

Explanations

phrases related to events or actions happening or being planned

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

me

-0.68

ãĥĹ

-0.61

edit

-0.58

Trivia

-0.57

lie

-0.57

idy

-0.57

stroke

-0.56

idium

-0.56

Reilly

-0.56

 Digest

-0.56

POSITIVE LOGITS

 ourselves

2.42

our

1.83

 ours

1.33

OUR

1.32

Our

1.21

Our

1.18

we

0.97

We

0.86

We

0.83

our

0.83

Activations Density 0.826%

phrases related to events or actions happening or being planned

No Comments

No Known Activations