INDEX

Explanations

words related to North Korea

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

rative

-0.73

ulous

-0.69

imental

-0.68

ername

-0.67

ration

-0.67

FAULT

-0.67

ATURE

-0.67

TED

-0.66

NRS

-0.66

ILA

-0.66

POSITIVE LOGITS

ampton

1.20

 Carolina

1.14

 Korea

1.10

western

1.04

 Pole

1.03

 Koreans

1.02

 Dakota

1.01

shore

0.93

umber

0.93

 Korean

0.92

Activations Density 0.253%

words related to North Korea

No Comments

No Known Activations