INDEX

Explanations

quotes or statements made by people

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

nown

-0.77

 Ames

-0.68

manship

-0.68

 Engel

-0.67

 Bach

-0.64

 Rath

-0.61

 blow

-0.60

isphere

-0.60

ighed

-0.59

 inhibited

-0.58

POSITIVE LOGITS

Interstitial

1.33

cause

1.26

Cause

1.24

taboola

1.22

Mech

1.18

til

1.12

tis

1.11

MpServer

1.06

-'

0.92

================================================================

0.89

Activations Density 1.078%

quotes or statements made by people

No Comments

No Known Activations