INDEX

Explanations

mentions of congratulations or announcements within a text

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

pmwiki

-0.78

IPS

-0.75

 Gleaming

-0.70

ical

-0.67

ICES

-0.67

BALL

-0.66

istics

-0.64

 Leilan

-0.62

istic

-0.62

 SPORTS

-0.61

POSITIVE LOGITS

regation

1.26

rats

1.25

regate

1.22

ression

1.08

ressive

1.00

resso

1.00

regor

0.97

cong

0.96

erest

0.95

ressor

0.92

Activations Density 0.043%

mentions of congratulations or announcements within a text

No Comments

No Known Activations