INDEX

Explanations

information related to crime and legal charges

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

Tokens

-1.03

soDeliveryDate

-0.83

arily

-0.80

 Mehran

-0.80

Tool

-0.78

options

-0.77

Parameters

-0.74

Score

-0.72

DragonMagazine

-0.71

Reviewed

-0.71

POSITIVE LOGITS

 felony

1.27

 misconduct

1.23

 wrongdoing

1.22

 conspiring

1.18

 misdemeanor

1.16

 crimes

1.16

 misdem

1.15

 manslaughter

1.11

 treason

1.11

 bribery

1.11

Activations Density 0.841%

information related to crime and legal charges

No Comments

No Known Activations