INDEX

Explanations

phrases related to political figures and international relations

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

crew

-0.77

MpServer

-0.76

kinson

-0.74

 dotted

-0.71

::::::::

-0.67

worldly

-0.64

pson

-0.62

dx

-0.62

 housed

-0.62

 panc

-0.61

POSITIVE LOGITS

 Barack

0.99

 Stephen

0.99

 Steve

0.95

 Donald

0.95

Tim

0.94

 Shinzo

0.94

 David

0.94

 Justin

0.93

 Tony

0.93

 Mitch

0.93

Activations Density 0.458%

phrases related to political figures and international relations

No Comments

No Known Activations