INDEX

Explanations

words related to legal matters and governmental affairs

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

ĪĴ

-0.80

rency

-0.78

OHN

-0.66

Honest

-0.66

nesia

-0.65

 peanuts

-0.63

bats

-0.62

rine

-0.62

etheless

-0.62

inki

-0.61

POSITIVE LOGITS

 IMAGES

0.78

 Getty

0.77

 Courtesy

0.75

AFP

0.74

 Provided

0.73

SPL

0.73

ãĥ¼ãĥ

0.71

 PHOTO

0.69

 Â©

0.68

 Valerie

0.67

Activations Density 0.915%

words related to legal matters and governmental affairs

No Comments

No Known Activations