INDEX

Explanations

the phrase "going to," especially when followed by another verb

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

CTV

-0.80

cius

-0.72

Reporting

-0.71

Pres

-0.70

amps

-0.68

checking

-0.68

quickShipAvailable

-0.65

mere

-0.64

 Provided

-0.61

VIDEO

-0.61

POSITIVE LOGITS

be

1.28

 lose

1.06

 continue

1.02

 stick

0.98

get

0.98

 make

0.97

 succeed

0.96

 regress

0.95

 give

0.95

 survive

0.94

Activations Density 0.549%

the phrase "going to," especially when followed by another verb

No Comments

No Known Activations