INDEX

Explanations

words related to legal proceedings and events

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

otide

-0.73

 conclud

-0.72

-0.68

asso

-0.67

Unique

-0.67

azaki

-0.67

è£ħ

-0.66

 distingu

-0.66

arium

-0.66

evidence

-0.65

POSITIVE LOGITS

 individuals

1.30

 persons

1.21

 youths

1.16

ness

1.15

 masses

1.08

 souls

1.07

 youngsters

1.05

 adults

1.03

 people

1.03

glers

0.99

Activations Density 1.462%

words related to legal proceedings and events

No Comments

No Known Activations