INDEX

Explanations

phrases related to self-identification or self-describing entities

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

 XIII

-0.76

IUM

-0.74

 Ashe

-0.71

 Rouge

-0.71

rium

-0.68

 Syndicate

-0.67

ICAN

-0.67

mingham

-0.66

 Nights

-0.66

ī

-0.65

POSITIVE LOGITS

destruct

1.23

lessly

1.09

 destruct

1.06

same

1.06

 explanatory

1.00

ridges

0.98

contained

0.95

conscious

0.90

proclaimed

0.89

pecially

0.87

Activations Density 0.022%

phrases related to self-identification or self-describing entities

No Comments

No Known Activations