INDEX

Explanations

proper nouns, specifically names of people and places

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

AAA

-0.68

unal

-0.68

ERAL

-0.64

EMBER

-0.64

ggle

-0.62

orate

-0.59

Lex

-0.57

ateurs

-0.56

CET

-0.56

 POLITICO

-0.56

POSITIVE LOGITS

ville

1.05

stown

1.03

 County

1.03

 Brothers

1.02

AFB

0.97

Collins

0.95

enegger

0.95

burg

0.95

et

0.94

sburg

0.93

Activations Density 1.464%

proper nouns, specifically names of people and places

No Comments

No Known Activations