INDEX

Explanations

locations or proper nouns

oai_token-act-pair · gpt-3.5-turbo

locations or place names

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Reincarn

-0.78

 crank

-0.77

 Logged

-0.69

 positives

-0.67

 compliment

-0.66

enegger

-0.66

 takedown

-0.66

*/(

-0.66

 toggle

-0.65

 glove

-0.65

POSITIVE LOGITS

ulia

1.04

ona

1.02

anya

0.99

avia

0.96

agar

0.96

areth

0.94

opolis

0.93

alia

0.93

amba

0.92

ark

0.92

Activations Density 0.360%

locations or proper nouns

locations or place names

No Comments

No Known Activations