INDEX

Explanations

statements expressing opinions or positions on political or social issues

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

!'

-0.62

 sqor

-0.60

 Byte

-0.58

 Illust

-0.57

llular

-0.56

 Streets

-0.56

 Entry

-0.56

 bask

-0.56

 gasp

-0.55

 Bunny

-0.55

POSITIVE LOGITS

"[

1.22

 "âĢ¦

1.13

"'

1.12

 "...

1.11

1.10

"#

0.99

 regretted

0.94

''

0.92

"(

0.91

""

0.85

Activations Density 7.541%

statements expressing opinions or positions on political or social issues

No Comments

No Known Activations