INDEX

Explanations

words related to mental states suggesting abnormal behavior, such as "lunatic"

oai_token-act-pair · gpt-3.5-turbo

references to lunacy and its variations in political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

âĢ¢âĢ¢

-0.75

 Norn

-0.74

Constructed

-0.72

ORN

-0.72

USE

-0.67

 Dome

-0.66

LECT

-0.65

åĬ

-0.64

EVA

-0.63

CHR

-0.62

POSITIVE LOGITS

acy

1.30

acies

1.29

cheon

1.26

atic

1.22

atics

1.18

atical

1.07

aries

1.06

aris

1.03

atural

1.02

acists

1.01

Activations Density 0.021%

words related to mental states suggesting abnormal behavior, such as "lunatic"

references to lunacy and its variations in political contexts

No Comments

No Known Activations