INDEX

Explanations

words related to being indestructible or impossible to remove or separate

oai_token-act-pair · gpt-3.5-turbo

words related to irreconcilable differences and conflicts

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CHO

-0.67

aeus

-0.65

NRS

-0.62

wine

-0.62

WR

-0.61

 Dani

-0.61

john

-0.57

ashtra

-0.56

sword

-0.56

BuyableInstoreAndOnline

-0.56

POSITIVE LOGITS

ably

1.42

ibly

1.37

ible

1.25

able

1.21

ence

1.03

ibility

1.03

ABLE

1.03

ibilities

1.02

ability

0.98

ences

0.95

Activations Density 0.092%

words related to being indestructible or impossible to remove or separate

words related to irreconcilable differences and conflicts

No Comments

No Known Activations