INDEX

Explanations

phrases related to statistics and rankings

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hops

-0.76

usa

-0.75

internal

-0.75

Interstitial

-0.75

peak

-0.72

EVA

-0.70

ICE

-0.67

akedown

-0.67

IFA

-0.67

AppData

-0.66

POSITIVE LOGITS

 youngster

1.26

 Frenchman

1.22

 veteran

1.20

 rapper

1.20

 singer

1.20

 actor

1.20

 former

1.20

 musician

1.18

 filmmaker

1.11

 elder

1.11

Activations Density 0.516%

phrases related to statistics and rankings

No Comments

No Known Activations