INDEX

Explanations

locations in China

oai_token-act-pair · gpt-3.5-turbo

names of cities or regions in China

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

 Sorceress

-0.71

 msec

-0.67

ODUCT

-0.64

 Normandy

-0.61

 vandal

-0.61

 à¤

-0.60

 horr

-0.60

 canv

-0.60

ORN

-0.59

=/

-0.59

POSITIVE LOGITS

jiang

1.52

zhou

1.35

hua

1.33

Yang

1.18

Hua

1.18

xi

1.17

jing

1.15

 Jiang

1.14

hai

1.14

 Guang

1.09

Activations Density 0.065%

locations in China

names of cities or regions in China

No Comments

No Known Activations