INDEX

Explanations

phrases related to events or occurrences happening repeatedly

oai_token-act-pair · gpt-3.5-turbo

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

 Spend

-0.64

 Deliver

-0.60

 inflic

-0.60

oyer

-0.58

 Doing

-0.56

 rejection

-0.56

UCT

-0.56

 consideration

-0.55

doing

-0.55

 premise

-0.55

POSITIVE LOGITS

 been

1.46

been

1.22

 arisen

1.08

 Been

1.02

 existed

0.95

 hitherto

0.94

bara

0.87

ritten

0.86

 emerged

0.83

Ŀ

0.81

Activations Density 0.043%

phrases related to events or occurrences happening repeatedly

No Comments

No Known Activations