INDEX

Explanations

the word "not" in sentences

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

Nice

-0.68

OSP

-0.63

å¥

-0.63

 Measures

-0.61

Kings

-0.60

Intern

-0.60

 Seasons

-0.59

Nine

-0.59

 assessments

-0.59

IDENT

-0.58

POSITIVE LOGITS

 necessarily

1.31

 tolerate

1.16

icably

1.11

 hesitate

1.07

 relent

1.01

ogle

1.00

be

0.99

 allow

0.97

hin

0.97

bud

0.94

Activations Density 0.071%

the word "not" in sentences

No Comments

No Known Activations