INDEX

Explanations

proper nouns related to individuals, locations, and companies

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

 Zimbabwe

-0.78

CRA

-0.75

PS

-0.74

 scorp

-0.73

é»Ĵ

-0.71

 Stan

-0.67

 microw

-0.67

ãģ¦

-0.67

-0.66

POSITIVE LOGITS

id

1.57

ID

1.30

idi

1.22

ids

1.18

idian

1.11

iden

1.11

aid

1.08

idy

1.07

IDs

1.07

ide

1.04

Activations Density 0.113%

proper nouns related to individuals, locations, and companies

No Comments

No Known Activations